{
  "schema": "agiranker.v3.board.1",
  "methodology": "methodology_v3",
  "engine": "v3_engine_1",
  "battery": {
    "id": "methodology_v3_battery_2026-10-01",
    "sha256": "a7446230cb10eed172f29cf173b844c5706d7b172b4c9731873311d95f9baa08"
  },
  "release": {
    "class": "evidence"
  },
  "attribution": "per_cell",
  "source": {
    "engine_result_sha256": "3183f800bee81a1fab25474ff854f06c2ef8f4ea803bc99fce4e1eb40ff8f759",
    "evidence_record_count": 948,
    "roster_count": 47
  },
  "counts": {
    "ranked": 13,
    "at_least": 17,
    "early_results": 17,
    "held": 0
  },
  "models": [
    {
      "model_id": "claude-opus-5-5",
      "display_name": "Claude Opus 5.5",
      "position": 1,
      "state": "ranked",
      "rank": 1,
      "provider": "Anthropic",
      "api_name": "claude-opus-5-5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 76.72479368867012,
      "minimum_score": null,
      "serving_label": "with refusal fallback",
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_claude-opus-5-5__terminal_bench_4_0__tb4_2026_10_23",
          "raw_score": 0.6515,
          "normalized": 65.14999999999999,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "excluded",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "enabled",
            "use": "confirmed_used"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CONFIRMED_USED"
          ],
          "serving_status": "fallback_used",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Claude Opus 5.5",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": 0
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_claude-opus-5-5__livebench_agentic_coding__v3_candidate_2026_10_23",
          "raw_score": 0.71717,
          "normalized": 71.717,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-opus-5-5-max-effort",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_claude-opus-5-5__arc_agi_2__v3_candidate_2026_10_23",
          "raw_score": 0.917,
          "normalized": 91.7,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Claude Opus 5.5 (Max)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_claude-opus-5-5__livebench_global_average__v3_candidate_2026_10_23",
          "raw_score": 0.8321657142857143,
          "normalized": 83.21657142857143,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-opus-5-5-max-effort",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_claude-opus-5-5__hle__v3_candidate_2026_10_23",
          "raw_score": 0.613531047265987,
          "normalized": 61.353104726598694,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "excluded",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "enabled",
            "use": "confirmed_used"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CONFIRMED_USED"
          ],
          "serving_status": "fallback_used",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Claude Opus 5.5 (Max, Default Fallback)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_claude-opus-5-5__mmmu_pro__v3_candidate_2026_10_23",
          "raw_score": 0.876878612716763,
          "normalized": 87.6878612716763,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "excluded",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "enabled",
            "use": "confirmed_used"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CONFIRMED_USED"
          ],
          "serving_status": "fallback_used",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Claude Opus 5.5 (Max, Default Fallback)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 75.719,
        "rank": 1,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_claude-opus-5-5__vibe_code_bench_1_1__v3_candidate_2026_10_23",
            "raw_score": 0.9029,
            "normalized": 90.29,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "held",
            "lifecycle": "current",
            "serving": {
              "capability": "possible",
              "policy": "unspecified",
              "use": "unknown"
            },
            "mode": "labelled",
            "reason_codes": [
              "FALLBACK_CAPABLE_SERVING_UNSTATED"
            ],
            "serving_status": "not_stated",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Claude Opus 5.5",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-6-astra",
      "display_name": "GPT-6 Astra",
      "position": 2,
      "state": "ranked",
      "rank": 2,
      "provider": "OpenAI",
      "api_name": "gpt-6-astra",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 73.02502298557863,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-6-astra__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.596,
          "normalized": 59.599999999999994,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-6 Astra",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 4.4
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-6-astra__livebench_agentic_coding__2026_09_06",
          "raw_score": 0.57323,
          "normalized": 57.323,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-6-astra-max",
            "date": "2026-09-06",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-6-astra__arc_agi_2__2026_09_06",
          "raw_score": 0.95,
          "normalized": 95,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/results/openai-gpt-6-astra",
            "row_label": "GPT-6 Astra (Max)",
            "date": "2026-09-02",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-6-astra__livebench_global_average__2026_09_06",
          "raw_score": 0.8216064285714288,
          "normalized": 82.16064285714289,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-6-astra-max",
            "date": "2026-09-06",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-6-astra__hle__2026_09_06",
          "raw_score": 0.547,
          "normalized": 54.7,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-6 Astra (max)",
            "date": "2026-09-06",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-6-astra__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.86878612716763,
          "normalized": 86.878612716763,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-6 Astra (max)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 68.83766666666666,
        "rank": 4,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-6-astra__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8959,
            "normalized": 89.59,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-6 Astra",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "claude-opus-5",
      "display_name": "Claude Opus 5",
      "position": 3,
      "state": "ranked",
      "rank": 3,
      "provider": "Anthropic",
      "api_name": "claude-opus-5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 71.19339900092407,
      "minimum_score": null,
      "serving_label": "with refusal fallback",
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_claude-opus-5__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.5353,
          "normalized": 53.53,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "excluded",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "enabled",
            "use": "confirmed_used"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CONFIRMED_USED"
          ],
          "serving_status": "fallback_used",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Claude Opus 5",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.34
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_claude-opus-5__livebench_agentic_coding__refresh_2026_08_05",
          "raw_score": 0.652,
          "normalized": 65.2,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "Claude 5 Opus Thinking Max Effort",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_claude-opus-5__arc_agi_2__v3_e1_2026_10_18_reattest",
          "raw_score": 0.904,
          "normalized": 90.4,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Claude Opus 5 (Max)",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_claude-opus-5__livebench_global_average__2026_08_22",
          "raw_score": 0.8008497619047619,
          "normalized": 80.08497619047618,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-opus-5-max-effort",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_claude-opus-5__hle__refresh_2026_08_19",
          "raw_score": 0.549,
          "normalized": 54.900000000000006,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "disabled",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Claude Opus 5 (max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_claude-opus-5__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.847398843930636,
          "normalized": 84.7398843930636,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "disabled",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Claude Opus 5 (Adaptive Reasoning, Max Effort)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 69.04333333333334,
        "rank": 3,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_claude-opus-5__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.884,
            "normalized": 88.4,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "held",
            "lifecycle": "current",
            "serving": {
              "capability": "possible",
              "policy": "unspecified",
              "use": "unknown"
            },
            "mode": "labelled",
            "reason_codes": [
              "FALLBACK_CAPABLE_SERVING_UNSTATED"
            ],
            "serving_status": "not_stated",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Claude Opus 5",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-6.1-sol",
      "display_name": "GPT-6.1 Sol",
      "position": 4,
      "state": "ranked",
      "rank": 4,
      "provider": "OpenAI",
      "api_name": "gpt-6.1-sol",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 71.0309460247284,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-6.1-sol__terminal_bench_4_0__tb4_2026_10_23",
          "raw_score": 0.5505,
          "normalized": 55.05,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-6.1 Sol",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": 1.82
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-6.1-sol__livebench_agentic_coding__v3_candidate_2026_10_23",
          "raw_score": 0.5454533333333333,
          "normalized": 54.54533333333333,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-6.1-sol-max",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-6.1-sol__arc_agi_2__v3_candidate_2026_10_23",
          "raw_score": 0.942,
          "normalized": 94.19999999999999,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GPT-6.1 Sol (Max)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-6.1-sol__livebench_global_average__v3_candidate_2026_10_23",
          "raw_score": 0.8161566666666666,
          "normalized": 81.61566666666667,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-6.1-sol-max",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-6.1-sol__hle__v3_candidate_2026_10_23",
          "raw_score": 0.529193697868397,
          "normalized": 52.919369786839695,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-6.1 Sol (Max)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-6.1-sol__mmmu_pro__v3_candidate_2026_10_23",
          "raw_score": 0.859537572254335,
          "normalized": 85.9537572254335,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-6.1 Sol (Max)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 66.17511111111111,
        "rank": 5,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-6.1-sol__vibe_code_bench_1_1__v3_candidate_2026_10_23",
            "raw_score": 0.8893,
            "normalized": 88.92999999999999,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-6.1 Sol",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-5.6-sol",
      "display_name": "ChatGPT 5.6 Sol",
      "position": 5,
      "state": "ranked",
      "rank": 5,
      "provider": "OpenAI",
      "api_name": "gpt-5.6-sol",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 66.24615393043923,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-5.6-sol__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.3788,
          "normalized": 37.88,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-5.6 Sol",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-5.6-sol__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.56212,
          "normalized": 56.211999999999996,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.6-sol-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-5.6-sol__arc_agi_2__v3_e1_2026_10_18_reattest",
          "raw_score": 0.925,
          "normalized": 92.5,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GPT-5.6 Sol (Max)",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-5.6-sol__livebench_global_average__2026_08_22",
          "raw_score": 0.8105354761904762,
          "normalized": 81.05354761904762,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.6-sol-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-5.6-sol__hle__refresh_2026_08_19",
          "raw_score": 0.495,
          "normalized": 49.5,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-5.6 Sol (max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-5.6-sol__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.834104046242775,
          "normalized": 83.4104046242775,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-5.6 Sol (max)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 58.197333333333326,
        "rank": 10,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-5.6-sol__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.805,
            "normalized": 80.5,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-5.6 Sol",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-6-sol",
      "display_name": "GPT-6 Sol",
      "position": 6,
      "state": "ranked",
      "rank": 6,
      "provider": "OpenAI",
      "api_name": "gpt-6-sol",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 66.02365984343159,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-6-sol__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.4444,
          "normalized": 44.440000000000005,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-6 Sol",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 3.54
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-6-sol__livebench_agentic_coding__v295_2026_10_01",
          "raw_score": 0.5287866666666666,
          "normalized": 52.87866666666666,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-6-sol-max",
            "date": "2026-10-01",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-6-sol__arc_agi_2__v295_2026_10_01",
          "raw_score": 0.896,
          "normalized": 89.60000000000001,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GPT-6 Sol (Max)",
            "date": "2026-10-01",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-6-sol__livebench_global_average__v293_2026_09_26",
          "raw_score": 0.7924545238095239,
          "normalized": 79.24545238095239,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "gpt-6-sol-max",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-6-sol__hle__v293_2026_09_26",
          "raw_score": 0.479147358665431,
          "normalized": 47.914735866543104,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-6 Sol (max)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-6-sol__mmmu_pro__v296_2026_10_18",
          "raw_score": 0.829479768786127,
          "normalized": 82.94797687861269,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-6 Sol (Max)",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 61.71288888888889,
        "rank": 6,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-6-sol__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8782,
            "normalized": 87.82,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-6 Sol",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gemini-3.8-flash",
      "display_name": "Gemini 3.8 Flash",
      "position": 7,
      "state": "ranked",
      "rank": 7,
      "provider": "Google",
      "api_name": "gemini-3.8-flash",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 60.35836997006607,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gemini-3.8-flash__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.197,
          "normalized": 19.7,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Gemini 3.8 Flash",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 2.31
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gemini-3.8-flash__livebench_agentic_coding",
          "raw_score": 0.5424233333333334,
          "normalized": 54.242333333333335,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.8-flash-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gemini-3.8-flash__arc_agi_2__v295_2026_10_01",
          "raw_score": 0.892,
          "normalized": 89.2,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Gemini 3.8 Flash (High)",
            "date": "2026-10-01",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gemini-3.8-flash__livebench_global_average",
          "raw_score": 0.758285,
          "normalized": 75.8285,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "gemini-3.8-flash-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gemini-3.8-flash__hle",
          "raw_score": 0.478,
          "normalized": 47.8,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Gemini 3.8 Flash (high)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gemini-3.8-flash__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.85606936416185,
          "normalized": 85.606936416185,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Gemini 3.8 Flash (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 50.86411111111111,
        "rank": 14,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gemini-3.8-flash__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.7865,
            "normalized": 78.64999999999999,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Gemini 3.8 Flash",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-5.6-terra",
      "display_name": "ChatGPT 5.6 Terra",
      "position": 8,
      "state": "ranked",
      "rank": 8,
      "provider": "OpenAI",
      "api_name": "gpt-5.6-terra",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 59.12763283425737,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-5.6-terra__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.2273,
          "normalized": 22.73,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-5.6 Terra",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 2.31
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-5.6-terra__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.5494966666666666,
          "normalized": 54.949666666666666,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.6-terra-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-5.6-terra__arc_agi_2",
          "raw_score": 0.839,
          "normalized": 83.89999999999999,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/results/openai-gpt-5-6-terra",
            "row_label": "GPT-5.6 Terra (Max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-5.6-terra__livebench_global_average__2026_08_22",
          "raw_score": 0.7793625,
          "normalized": 77.93625,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.6-terra-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-5.6-terra__hle__reattest_2026-08-08",
          "raw_score": 0.429101019462465,
          "normalized": 42.9101019462465,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-5.6 Terra (max)",
            "date": "2026-08-08",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-5.6-terra__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.806936416184971,
          "normalized": 80.6936416184971,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-5.6 Terra (max)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 50.75655555555556,
        "rank": 15,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-5.6-terra__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.7459,
            "normalized": 74.59,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-5.6 Terra",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gemini-3.7-flash",
      "display_name": "Gemini 3.7 Flash",
      "position": 9,
      "state": "ranked",
      "rank": 9,
      "provider": "Google",
      "api_name": "gemini-3.7-flash",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 58.82812502678817,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gemini-3.7-flash__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.1212,
          "normalized": 12.120000000000001,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Gemini 3.7 Flash",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 3.03
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gemini-3.7-flash__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.58283,
          "normalized": 58.282999999999994,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.7-flash-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gemini-3.7-flash__arc_agi_2",
          "raw_score": 0.846,
          "normalized": 84.6,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Gemini 3.7 Flash (High)",
            "date": "2026-08-13",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gemini-3.7-flash__livebench_global_average__2026_08_22",
          "raw_score": 0.788260119047619,
          "normalized": 78.8260119047619,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.7-flash-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gemini-3.7-flash__hle",
          "raw_score": 0.479,
          "normalized": 47.9,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Gemini 3.7 Flash (high)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gemini-3.7-flash__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.854913294797688,
          "normalized": 85.4913294797688,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Gemini 3.7 Flash (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 46.931000000000004,
        "rank": 21,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gemini-3.7-flash__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.7039,
            "normalized": 70.39,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Gemini 3.7 Flash",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-5.5",
      "display_name": "ChatGPT 5.5",
      "position": 10,
      "state": "at_least",
      "rank": null,
      "provider": "OpenAI",
      "api_name": "gpt-5.5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 55.01104271685243,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-5.5__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.5398966666666667,
          "normalized": 53.98966666666667,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.5-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-5.5__arc_agi_2__refresh_2026_08_12",
          "raw_score": 0.85,
          "normalized": 85,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GPT-5.5 (XHigh)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-5.5__livebench_global_average__2026_08_22",
          "raw_score": 0.8018829761904762,
          "normalized": 80.18829761904762,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.5-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-5.5__hle__v293_2026_09_26",
          "raw_score": 0.457831325301205,
          "normalized": 45.783132530120504,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-5.5 (xhigh)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-5.5__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.798843930635838,
          "normalized": 79.8843930635838,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-5.5 (xhigh)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "kimi-k3",
      "display_name": "Kimi K3",
      "position": 11,
      "state": "ranked",
      "rank": 10,
      "provider": "Moonshot",
      "api_name": "kimi-k3",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 54.80062846924029,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_kimi-k3__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.1717,
          "normalized": 17.169999999999998,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Kimi K3",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_kimi-k3__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.6217166666666666,
          "normalized": 62.17166666666666,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "kimi-k3",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_kimi-k3__arc_agi_2",
          "raw_score": 0.604,
          "normalized": 60.4,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Kimi K3 (Max)",
            "date": "2026-07-16",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_kimi-k3__livebench_global_average__refresh_2026_08_12",
          "raw_score": 0.79193,
          "normalized": 79.193,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "kimi-k3",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_kimi-k3__hle__refresh_2026_08_19",
          "raw_score": 0.469,
          "normalized": 46.9,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Kimi K3 (max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_kimi-k3__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.805202312138728,
          "normalized": 80.52023121387279,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Kimi K3 (max)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 54.77055555555555,
        "rank": 12,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_kimi-k3__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8497,
            "normalized": 84.97,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Kimi K3",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gemini-3.5-flash",
      "display_name": "Gemini 3.5 Flash",
      "position": 12,
      "state": "ranked",
      "rank": 11,
      "provider": "Google DeepMind",
      "api_name": "gemini-3.5-flash",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 52.010847762083024,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gemini-3.5-flash__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0606,
          "normalized": 6.0600000000000005,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Gemini 3.5 Flash",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gemini-3.5-flash__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.48989666666666665,
          "normalized": 48.989666666666665,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.5-flash-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gemini-3.5-flash__arc_agi_2__refresh_2026_08_12",
          "raw_score": 0.721,
          "normalized": 72.1,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Gemini 3.5 Flash (High)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gemini-3.5-flash__livebench_global_average__v3_e1_2026_10_18_reattest",
          "raw_score": 0.746377619047619,
          "normalized": 74.6377619047619,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.5-flash-high",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gemini-3.5-flash__hle__v293_2026_09_26",
          "raw_score": 0.42678405931418,
          "normalized": 42.678405931418,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Gemini 3.5 Flash (high)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gemini-3.5-flash__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.842774566473988,
          "normalized": 84.2774566473988,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Gemini 3.5 Flash (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 34.57655555555556,
        "rank": 24,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gemini-3.5-flash__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.4868,
            "normalized": 48.68,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Gemini 3.5 Flash",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-6-luna",
      "display_name": "GPT-6 Luna",
      "position": 13,
      "state": "ranked",
      "rank": 12,
      "provider": "OpenAI",
      "api_name": "gpt-6-luna",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 49.6974834354882,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-6-luna__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.1364,
          "normalized": 13.639999999999999,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-6 Luna",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-6-luna__livebench_agentic_coding__v295_2026_10_01",
          "raw_score": 0.5121199999999999,
          "normalized": 51.21199999999999,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-6-luna-max",
            "date": "2026-10-01",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-6-luna__arc_agi_2__a2_2026_09_24",
          "raw_score": 0.593,
          "normalized": 59.3,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GPT-6 Luna (Max)",
            "date": "2026-09-24",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-6-luna__livebench_global_average__v293_2026_09_26",
          "raw_score": 0.7202647619047619,
          "normalized": 72.02647619047619,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "gpt-6-luna-max",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-6-luna__hle__v293_2026_09_26",
          "raw_score": 0.385078776645042,
          "normalized": 38.5078776645042,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-6 Luna (max)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-6-luna__mmmu_pro__v296_2026_10_18",
          "raw_score": 0.796531791907514,
          "normalized": 79.6531791907514,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-6 Luna (Max)",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 48.834,
        "rank": 19,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-6-luna__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8165,
            "normalized": 81.65,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-6 Luna",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "grok-4.5",
      "display_name": "Grok 4.5",
      "position": 14,
      "state": "ranked",
      "rank": 13,
      "provider": "xAI",
      "api_name": "grok-4.5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "AGI Score",
      "official_score": 49.287631560232924,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_grok-4.5__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0859,
          "normalized": 8.59,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Grok 4.5",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.34
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_grok-4.5__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.5646466666666666,
          "normalized": 56.464666666666666,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "grok-4.5",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_grok-4.5__arc_agi_2__v3_e1_2026_10_18_reattest",
          "raw_score": 0.526,
          "normalized": 52.6,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Grok 4.5 (High)",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_grok-4.5__livebench_global_average__refresh_2026_08_12",
          "raw_score": 0.757728,
          "normalized": 75.77279999999999,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "grok-4.5",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_grok-4.5__hle__v293_2026_09_26",
          "raw_score": 0.42678405931418,
          "normalized": 42.678405931418,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Grok 4.5 (high)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_grok-4.5__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.804046242774566,
          "normalized": 80.4046242774566,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Grok 4.5 (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [],
      "coding": {
        "score": 44.684888888888885,
        "rank": 22,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_grok-4.5__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.69,
            "normalized": 69,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Grok 4.5",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "glm-5.3-flash",
      "display_name": "GLM 5.3 Flash",
      "position": 15,
      "state": "at_least",
      "rank": null,
      "provider": "Z.ai",
      "api_name": "glm-5.3-flash",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 48.3240874631887,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_glm-5.3-flash__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.3737,
          "normalized": 37.37,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GLM 5.3 Flash",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 2.67
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_glm-5.3-flash__livebench_agentic_coding",
          "raw_score": 0.5676766666666666,
          "normalized": 56.76766666666666,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "glm-5.3-flash",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_glm-5.3-flash__arc_agi_2",
          "raw_score": 0.658,
          "normalized": 65.8,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GLM-5.3-Flash (Max)",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_glm-5.3-flash__livebench_global_average",
          "raw_score": 0.7159078571428572,
          "normalized": 71.59078571428572,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "glm-5.3-flash",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_glm-5.3-flash__hle",
          "raw_score": 0.398517145505097,
          "normalized": 39.8517145505097,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GLM-5.3-Flash",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 41.63255555555555,
        "rank": 23,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_glm-5.3-flash__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.3076,
            "normalized": 30.759999999999998,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GLM 5.3 Flash",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gemini-3.6-flash",
      "display_name": "Gemini 3.6 Flash",
      "position": 16,
      "state": "at_least",
      "rank": null,
      "provider": "Google",
      "api_name": "gemini-3.6-flash",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 46.94798203437961,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_gemini-3.6-flash__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.43434333333333336,
          "normalized": 43.434333333333335,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.6-flash-high",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gemini-3.6-flash__arc_agi_2",
          "raw_score": 0.604,
          "normalized": 60.4,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Gemini 3.6 Flash (High)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gemini-3.6-flash__livebench_global_average__2026_08_22",
          "raw_score": 0.7358751190476189,
          "normalized": 73.5875119047619,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.6-flash-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gemini-3.6-flash__hle__v293_2026_09_26",
          "raw_score": 0.408248378127896,
          "normalized": 40.824837812789596,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Gemini 3.6 Flash (high)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gemini-3.6-flash__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.832369942196532,
          "normalized": 83.2369942196532,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Gemini 3.6 Flash (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "grok-4.7",
      "display_name": "Grok 4.7",
      "position": 17,
      "state": "at_least",
      "rank": null,
      "provider": "xAI",
      "api_name": "grok-4.7",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 46.72634376729051,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_grok-4.7__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.2879,
          "normalized": 28.79,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Grok 4.7",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 2.31
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_grok-4.7__livebench_agentic_coding__v295_2026_10_01",
          "raw_score": 0.5398966666666667,
          "normalized": 53.98966666666667,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "grok-4.7-xhigh",
            "date": "2026-10-01",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_grok-4.7__arc_agi_2",
          "raw_score": 0.614,
          "normalized": 61.4,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Grok 4.7 (XHigh)",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_grok-4.7__livebench_global_average__v293_2026_09_26",
          "raw_score": 0.7739673809523809,
          "normalized": 77.39673809523809,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "grok-4.7-xhigh",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_grok-4.7__hle__v293_2026_09_26",
          "raw_score": 0.431417979610751,
          "normalized": 43.1417979610751,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Grok 4.7 (xhigh)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 56.31655555555556,
        "rank": 11,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_grok-4.7__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8617,
            "normalized": 86.17,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Grok 4.7",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gpt-5.6-luna",
      "display_name": "ChatGPT 5.6 Luna",
      "position": 18,
      "state": "at_least",
      "rank": null,
      "provider": "OpenAI",
      "api_name": "gpt-5.6-luna",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 46.69605508273788,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_gpt-5.6-luna__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.48434333333333335,
          "normalized": 48.434333333333335,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.6-luna-max",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_gpt-5.6-luna__arc_agi_2",
          "raw_score": 0.595,
          "normalized": 59.5,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/results/openai-gpt-5-6-luna",
            "row_label": "GPT-5.6 Luna (Max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_gpt-5.6-luna__livebench_global_average__2026_08_22",
          "raw_score": 0.7355938095238095,
          "normalized": 73.55938095238095,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gpt-5.6-luna-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_gpt-5.6-luna__hle__reattest_2026-08-08",
          "raw_score": 0.394810009267841,
          "normalized": 39.4810009267841,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-5.6 Luna (max)",
            "date": "2026-08-08",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-5.6-luna__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.785549132947977,
          "normalized": 78.5549132947977,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-5.6 Luna (max)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "CHECKPOINT_UNRESOLVED"
          ],
          "line_code": "CHECKPOINT_UNRESOLVED",
          "line": "Terminal-Bench 4.0: Vals does not state which checkpoint of the model it tested"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "grok-4.6",
      "display_name": "Grok 4.6",
      "position": 19,
      "state": "at_least",
      "rank": null,
      "provider": "xAI",
      "api_name": "grok-4.6",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 46.01992266020125,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_grok-4.6__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.1717,
          "normalized": 17.169999999999998,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Grok 4.6",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.34
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_grok-4.6__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.5702,
          "normalized": 57.02,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "grok-4.6",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_grok-4.6__arc_agi_2",
          "raw_score": 0.671,
          "normalized": 67.10000000000001,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Grok 4.6 (XHigh)",
            "date": "2026-08-11",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_grok-4.6__livebench_global_average__2026_08_22",
          "raw_score": 0.78042,
          "normalized": 78.042,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "grok-4.6",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_grok-4.6__hle__v293_2026_09_26",
          "raw_score": 0.440685820203893,
          "normalized": 44.0685820203893,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Grok 4.6 (xhigh)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 50.14333333333334,
        "rank": 18,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_grok-4.6__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.7624,
            "normalized": 76.24,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Grok 4.6",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "qwen-3.8-27b",
      "display_name": "Qwen 3.8 27B",
      "position": 20,
      "state": "at_least",
      "rank": null,
      "provider": "Alibaba",
      "api_name": "qwen-3.8-27b",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 44.08144033985804,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_qwen-3.8-27b__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.6136366666666667,
          "normalized": 61.363666666666674,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "qwen3.8-27b",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_qwen-3.8-27b__arc_agi_2",
          "raw_score": 0.424,
          "normalized": 42.4,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Qwen3.8-27B (XHigh)",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_qwen-3.8-27b__livebench_global_average__2026_08_22",
          "raw_score": 0.7526910714285714,
          "normalized": 75.26910714285714,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "qwen3.8-27b",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_qwen-3.8-27b__hle__reconcile_2026_08_20",
          "raw_score": 0.33920296570899,
          "normalized": 33.920296570899,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Qwen3.8 27B",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_qwen-3.8-27b__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.763005780346821,
          "normalized": 76.3005780346821,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Qwen3.8 27B (xhigh)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "claude-sonnet-5-5",
      "display_name": "Claude Sonnet 5.5",
      "position": 21,
      "state": "at_least",
      "rank": null,
      "provider": "Anthropic",
      "api_name": "claude-sonnet-5-5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 43.502686044334325,
      "serving_label": "with refusal fallback",
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_claude-sonnet-5-5__terminal_bench_4_0__tb4_2026_10_23",
          "raw_score": 0.6414,
          "normalized": 64.14,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "excluded",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "enabled",
            "use": "confirmed_used"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CONFIRMED_USED"
          ],
          "serving_status": "fallback_used",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Claude Sonnet 5.5",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": 1.01
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_claude-sonnet-5-5__livebench_agentic_coding__v3_candidate_2026_10_23",
          "raw_score": 0.5631333333333334,
          "normalized": 56.31333333333334,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-sonnet-5-5-max-effort",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_claude-sonnet-5-5__livebench_global_average__v3_candidate_2026_10_23",
          "raw_score": 0.7567214285714284,
          "normalized": 75.67214285714284,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "held",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "unspecified",
            "use": "unknown"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CAPABLE_SERVING_UNSTATED"
          ],
          "serving_status": "not_stated",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-sonnet-5-5-max-effort",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_claude-sonnet-5-5__hle__v3_candidate_2026_10_23",
          "raw_score": 0.549582947173309,
          "normalized": 54.9582947173309,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "excluded",
          "lifecycle": "current",
          "serving": {
            "capability": "possible",
            "policy": "enabled",
            "use": "confirmed_used"
          },
          "mode": "labelled",
          "reason_codes": [
            "FALLBACK_CONFIRMED_USED"
          ],
          "serving_status": "fallback_used",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Claude Sonnet 5.5 (Max, Default Fallback)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "LISTED_NO_TOP_VALUE"
          ],
          "line_code": "LISTED_NO_TOP_VALUE",
          "line": "ARC-AGI-2: listed by ARC Prize, no score published at its top setting"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 70.94777777777779,
        "rank": 2,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_claude-sonnet-5-5__vibe_code_bench_1_1__v3_candidate_2026_10_23",
            "raw_score": 0.9239,
            "normalized": 92.39,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "held",
            "lifecycle": "current",
            "serving": {
              "capability": "possible",
              "policy": "unspecified",
              "use": "unknown"
            },
            "mode": "labelled",
            "reason_codes": [
              "FALLBACK_CAPABLE_SERVING_UNSTATED"
            ],
            "serving_status": "not_stated",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Claude Sonnet 5.5",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "deepseek-v4-pro-0813",
      "display_name": "DeepSeek V4 Pro 0813",
      "position": 22,
      "state": "at_least",
      "rank": null,
      "provider": "DeepSeek",
      "api_name": "deepseek-v4-pro-0813",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 43.31287426785714,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_deepseek-v4-pro-0813__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.1414,
          "normalized": 14.14,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "DeepSeek V4 Pro 0813",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 2.02
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_deepseek-v4-pro-0813__livebench_agentic_coding",
          "raw_score": 0.549497,
          "normalized": 54.9497,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "deepseek-v4-pro-0813",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": {
          "evidence_id": "ev_deepseek-v4-pro-0813__arc_agi_2__v295_2026_10_01",
          "raw_score": 0.613,
          "normalized": 61.3,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "DeepSeek V4 Pro 0813 (Max)",
            "date": "2026-10-01",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": {
          "evidence_id": "ev_deepseek-v4-pro-0813__livebench_global_average",
          "raw_score": 0.774361,
          "normalized": 77.4361,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "deepseek-v4-pro-0813",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_deepseek-v4-pro-0813__hle__refresh_2026_08_19",
          "raw_score": 0.41,
          "normalized": 41,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "DeepSeek V4 Pro 0813 (max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 50.463233333333335,
        "rank": 16,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_deepseek-v4-pro-0813__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.823,
            "normalized": 82.3,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "DeepSeek V4 Pro 0813",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "claude-sonnet-5",
      "display_name": "Claude Sonnet 5",
      "position": 23,
      "state": "at_least",
      "rank": null,
      "provider": "Anthropic",
      "api_name": "claude-sonnet-5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 38.71519544369035,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_claude-sonnet-5__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.1061,
          "normalized": 10.61,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Claude Sonnet 5",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_claude-sonnet-5__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.59394,
          "normalized": 59.394000000000005,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-sonnet-5-xhigh-effort",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_claude-sonnet-5__livebench_global_average__2026_08_22",
          "raw_score": 0.7603971428571428,
          "normalized": 76.03971428571428,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-sonnet-5-xhigh-effort",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_claude-sonnet-5__hle__v3_aa_reread_2026_10_21",
          "raw_score": 0.412882298424467,
          "normalized": 41.2882298424467,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Claude Sonnet 5 (Max)",
            "date": "2026-10-21",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_claude-sonnet-5__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.772832369942197,
          "normalized": 77.28323699421969,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Claude Sonnet 5 (Adaptive Reasoning, Max Effort)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        }
      ],
      "coding": {
        "score": 50.44466666666667,
        "rank": 17,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_claude-sonnet-5__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8133,
            "normalized": 81.33,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Claude Sonnet 5",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "glm-5.3",
      "display_name": "GLM 5.3",
      "position": 24,
      "state": "at_least",
      "rank": null,
      "provider": "Z.ai",
      "api_name": "glm-5.3",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 36.76303902863417,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_glm-5.3__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.3889,
          "normalized": 38.89,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GLM 5.3",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.82
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_glm-5.3__livebench_agentic_coding",
          "raw_score": 0.60909,
          "normalized": 60.909,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "glm-5.3",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_glm-5.3__livebench_global_average",
          "raw_score": 0.7613780952380952,
          "normalized": 76.13780952380952,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "glm-5.3",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_glm-5.3__hle",
          "raw_score": 0.422613531047266,
          "normalized": 42.2613531047266,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GLM-5.3 (max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 59.309666666666665,
        "rank": 8,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_glm-5.3__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.7813,
            "normalized": 78.13,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GLM 5.3",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "muse-spark-1.3",
      "display_name": "Muse Spark 1.3",
      "position": 25,
      "state": "at_least",
      "rank": null,
      "provider": "Meta",
      "api_name": "muse-spark-1.3",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 36.050439883258306,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_muse-spark-1.3__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.2475,
          "normalized": 24.75,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Muse Spark 1.3 Max",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_muse-spark-1.3__livebench_agentic_coding",
          "raw_score": 0.64091,
          "normalized": 64.091,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "muse-spark-1.3-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_muse-spark-1.3__livebench_global_average",
          "raw_score": 0.815886,
          "normalized": 81.5886,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "muse-spark-1.3-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_muse-spark-1.3__hle__v293_2026_09_26",
          "raw_score": 0.487025023169602,
          "normalized": 48.7025023169602,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Muse Spark 1.3 (max)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "FRONTIER_RUNG_ABSENT_ON_BOARD"
          ],
          "line_code": "FRONTIER_RUNG_ABSENT_ON_BOARD",
          "line": "MMMU-Pro: Artificial Analysis shows no result for the model's top effort setting"
        }
      ],
      "coding": {
        "score": 58.233666666666664,
        "rank": 9,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_muse-spark-1.3__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8586,
            "normalized": 85.86,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Muse Spark 1.3 Max",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "claude-haiku-5-5",
      "display_name": "Claude Haiku 5.5",
      "position": 26,
      "state": "at_least",
      "rank": null,
      "provider": "Anthropic",
      "api_name": "claude-haiku-5-5",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 34.529176756988704,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_claude-haiku-5-5__terminal_bench_4_0__tb4_2026_10_23",
          "raw_score": 0.3636,
          "normalized": 36.36,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "disabled",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Claude Haiku 5.5",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": 2.31
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_claude-haiku-5-5__livebench_agentic_coding__v3_candidate_2026_10_23",
          "raw_score": 0.5717166666666667,
          "normalized": 57.17166666666667,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-haiku-5-5-max-effort",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_claude-haiku-5-5__livebench_global_average__v3_candidate_2026_10_23",
          "raw_score": 0.6788196428571428,
          "normalized": 67.88196428571428,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "claude-haiku-5-5-max-effort",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_claude-haiku-5-5__hle__v3_candidate_2026_10_23",
          "raw_score": 0.443929564411492,
          "normalized": 44.3929564411492,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Claude Haiku 5.5 (Max)",
            "date": "2026-10-23",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "LISTED_NO_TOP_VALUE"
          ],
          "line_code": "LISTED_NO_TOP_VALUE",
          "line": "ARC-AGI-2: listed by ARC Prize, no score published at its top setting"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 61.32388888888889,
        "rank": 7,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_claude-haiku-5-5__vibe_code_bench_1_1__v3_candidate_2026_10_23",
            "raw_score": 0.9044,
            "normalized": 90.44,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Claude Haiku 5.5",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "claude-opus-4-8-thinking",
      "display_name": "Claude Opus 4.8 (thinking)",
      "position": 27,
      "state": "at_least",
      "rank": null,
      "provider": "Anthropic",
      "api_name": "claude-opus-4-8-thinking",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 32.94621482424201,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_claude-opus-4-8-thinking__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.2323,
          "normalized": 23.23,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Claude Opus 4.8",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.34
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_claude-opus-4-8-thinking__livebench_agentic_coding__refresh_2026_08_05",
          "raw_score": 0.505,
          "normalized": 50.5,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "Claude 4.8 Opus Thinking Max Effort",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_claude-opus-4-8-thinking__livebench_global_average__refresh_2026_08_12",
          "raw_score": 0.76224,
          "normalized": 76.224,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "claude-opus-4-8-max-effort",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_claude-opus-4-8-thinking__hle__v293_2026_09_26",
          "raw_score": 0.486561631139944,
          "normalized": 48.6561631139944,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Claude Opus 4.8 (Adaptive Reasoning, Max Effort)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "BENCHMARK_IDENTITY_NOT_PINNED",
            "CONFIGURATION_UNRESOLVED",
            "NO_SOURCE_ROW_ANCHOR"
          ],
          "line_code": "BENCHMARK_IDENTITY_NOT_PINNED",
          "line": "ARC-AGI-2: the ARC Prize result on record is for a different version of the test"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 52.15,
        "rank": 13,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_claude-opus-4-8-thinking__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.8272,
            "normalized": 82.72,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Claude Opus 4.8",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "inkling",
      "display_name": "Inkling",
      "position": 28,
      "state": "at_least",
      "rank": null,
      "provider": "Thinking Machines",
      "api_name": "inkling",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 32.612552461601986,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_inkling__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0051,
          "normalized": 0.51,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Inkling",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_inkling__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.49394000000000005,
          "normalized": 49.394000000000005,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "inkling-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_inkling__livebench_global_average__refresh_2026_08_12",
          "raw_score": 0.719224,
          "normalized": 71.9224,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "inkling-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_inkling__hle__refresh_2026_08_19",
          "raw_score": 0.319,
          "normalized": 31.900000000000002,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Inkling",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_inkling__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.734682080924856,
          "normalized": 73.4682080924856,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Inkling (xhigh)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "ARC-AGI-2: the ARC Prize result on record has not yet passed the v3 evidence check"
        }
      ],
      "coding": {
        "score": 23.038,
        "rank": 27,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_inkling__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.1921,
            "normalized": 19.21,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Inkling",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "muse-spark-1.2",
      "display_name": "Muse Spark 1.2",
      "position": 29,
      "state": "at_least",
      "rank": null,
      "provider": "Meta",
      "api_name": "muse-spark-1.2",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 29.955836966404075,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_muse-spark-1.2__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0606,
          "normalized": 6.0600000000000005,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Muse Spark 1.2",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_muse-spark-1.2__livebench_agentic_coding",
          "raw_score": 0.5757566666666666,
          "normalized": 57.575666666666656,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "muse-spark-1.2-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_muse-spark-1.2__livebench_global_average",
          "raw_score": 0.779548,
          "normalized": 77.9548,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "muse-spark-1.2-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_muse-spark-1.2__hle__reattest_2026-08-08",
          "raw_score": 0.454587581093605,
          "normalized": 45.458758109360495,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/articles/muse-spark-1-2",
            "row_label": "Muse Spark 1.2 (xhigh)",
            "date": "2026-08-08",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": 47.57855555555556,
        "rank": 20,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_muse-spark-1.2__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.791,
            "normalized": 79.10000000000001,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Muse Spark 1.2",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "grok-4.3",
      "display_name": "Grok 4.3",
      "position": 30,
      "state": "at_least",
      "rank": null,
      "provider": "xAI",
      "api_name": "grok-4.3",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": "at least",
      "official_score": null,
      "minimum_score": 27.986866785175295,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_grok-4.3__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.18535333333333334,
          "normalized": 18.535333333333334,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "grok-4.3",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_grok-4.3__livebench_global_average__v1_11_27__v3_e1_2026_10_18_reattest",
          "raw_score": 0.6224735714285714,
          "normalized": 62.24735714285714,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "grok-4.3",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_grok-4.3__hle__v293_2026_09_26",
          "raw_score": 0.372103799814643,
          "normalized": 37.2103799814643,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Grok 4.3 (high)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_grok-4.3__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.78092485549133,
          "normalized": 78.09248554913299,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Grok 4.3 (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "gpt-5.5-pro",
      "display_name": "ChatGPT 5.5 (Pro)",
      "position": 31,
      "state": "early_results",
      "rank": null,
      "provider": "OpenAI",
      "api_name": "gpt-5.5-pro",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": null,
        "arc_agi_2": {
          "evidence_id": "ev_gpt-5.5-pro__arc_agi_2__refresh_2026_08_12",
          "raw_score": 0.842,
          "normalized": 84.2,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "GPT-5.5 Pro (XHigh)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "livebench_global_average": null,
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NO_EVALUATOR_IDENTITY"
          ],
          "line_code": "NO_EVALUATOR_IDENTITY",
          "line": "Terminal-Bench 4.0: no Vals entry is matched to this model"
        },
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "Humanity's Last Exam: no Artificial Analysis result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "MMMU-Pro: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "livebench_agentic_coding",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "glm-5.2",
      "display_name": "GLM 5.2",
      "position": 32,
      "state": "early_results",
      "rank": null,
      "provider": "Z.AI",
      "api_name": "glm-5.2",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_glm-5.2__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.5176766666666667,
          "normalized": 51.76766666666667,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "glm-5.2",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_glm-5.2__livebench_global_average__2026_08_22",
          "raw_score": 0.7315728571428572,
          "normalized": 73.15728571428572,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "glm-5.2",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_glm-5.2__hle__refresh_2026_08_19",
          "raw_score": 0.411,
          "normalized": 41.099999999999994,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GLM-5.2 (max)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "ARC-AGI-2: the ARC Prize result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "gpt-6.1-terra",
      "display_name": "GPT-6.1 Terra",
      "position": 33,
      "state": "early_results",
      "rank": null,
      "provider": "OpenAI",
      "api_name": "gpt-6.1-terra",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gpt-6.1-terra__terminal_bench_4_0__tb4_2026_10_27",
          "raw_score": 0.4949,
          "normalized": 49.49,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "GPT-6.1 Terra",
            "date": "2026-10-27",
            "date_kind": "read",
            "standard_error_pp": 1.82
          }
        },
        "livebench_agentic_coding": null,
        "arc_agi_2": null,
        "livebench_global_average": null,
        "hle": {
          "evidence_id": "ev_gpt-6.1-terra__hle__v3_candidate_2026_10_27",
          "raw_score": 0.462465245597776,
          "normalized": 46.246524559777605,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "GPT-6.1 Terra (Max)",
            "date": "2026-10-27",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_gpt-6.1-terra__mmmu_pro__v3_candidate_2026_10_27",
          "raw_score": 0.846820809248555,
          "normalized": 84.6820809248555,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "GPT-6.1 Terra (Max)",
            "date": "2026-10-27",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "livebench_agentic_coding"
        ],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gpt-6.1-terra__vibe_code_bench_1_1__v3_candidate_2026_10_27",
            "raw_score": 0.84,
            "normalized": 84,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "GPT-6.1 Terra",
              "date": "2026-10-27",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gemini-3.1-pro-preview",
      "display_name": "Gemini 3.1 Pro (preview)",
      "position": 34,
      "state": "early_results",
      "rank": null,
      "provider": "Google DeepMind",
      "api_name": "gemini-3.1-pro-preview",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gemini-3.1-pro-preview__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0252,
          "normalized": 2.52,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Gemini 3.1 Pro Preview (02/26)",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0.51
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_gemini-3.1-pro-preview__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.4414133333333334,
          "normalized": 44.141333333333336,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "gemini-3.1-pro-preview-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_gemini-3.1-pro-preview__livebench_global_average__refresh_2026_08_12",
          "raw_score": 0.769518,
          "normalized": 76.9518,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "gemini-3.1-pro-preview-high",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "ARC-AGI-2: the ARC Prize result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "MMMU-Pro: Artificial Analysis does not state the configuration it tested"
        }
      ],
      "coding": {
        "score": 26.230444444444444,
        "rank": 26,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gemini-3.1-pro-preview__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.3203,
            "normalized": 32.029999999999994,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Gemini 3.1 Pro Preview (02/26)",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "gemini-4-argon",
      "display_name": "Gemini 4 Argon",
      "position": 35,
      "state": "early_results",
      "rank": null,
      "provider": "Google",
      "api_name": "gemini-4-argon",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_gemini-4-argon__terminal_bench_4_0__tb4_2026_10_21",
          "raw_score": 0.5758,
          "normalized": 57.58,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Gemini 4 Argon",
            "date": "2026-10-21",
            "date_kind": "read",
            "standard_error_pp": 2.31
          }
        },
        "livebench_agentic_coding": null,
        "arc_agi_2": {
          "evidence_id": "ev_gemini-4-argon__arc_agi_2__v297_2026_10_18",
          "raw_score": 0.913,
          "normalized": 91.3,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/leaderboard",
            "row_label": "Gemini 4 Argon (High)",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": null,
        "hle": {
          "evidence_id": "ev_gemini-4-argon__hle__v297_2026_10_18",
          "raw_score": 0.570898980537535,
          "normalized": 57.089898053753494,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Gemini 4 Argon (High)",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "livebench_agentic_coding"
        ],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_gemini-4-argon__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.9191,
            "normalized": 91.91,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Gemini 4 Argon",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "inkling-small",
      "display_name": "Inkling Small",
      "position": 36,
      "state": "early_results",
      "rank": null,
      "provider": "Thinking Machines",
      "api_name": "inkling-small",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_inkling-small__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0,
          "normalized": 0,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "Inkling Small",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0
          }
        },
        "livebench_agentic_coding": null,
        "arc_agi_2": {
          "evidence_id": "ev_inkling-small__arc_agi_2__reattest_2026-09-05",
          "raw_score": 0.401,
          "normalized": 40.1,
          "value_derivation": "direct_read",
          "benchmark_identity": "arc-prize/arc-agi-2/semi-private",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "ARC Prize",
            "url": "https://arcprize.org/results/thinky-inkling-small",
            "row_label": "Inkling Small (XHigh)",
            "date": "2026-09-05",
            "date_kind": "evaluated",
            "standard_error_pp": null
          }
        },
        "livebench_global_average": null,
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "MMMU-Pro: Artificial Analysis does not state the configuration it tested"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "livebench_agentic_coding"
        ],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_inkling-small__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.1905,
            "normalized": 19.05,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "Inkling Small",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "kimi-k2.6",
      "display_name": "Kimi K2.6",
      "position": 37,
      "state": "early_results",
      "rank": null,
      "provider": "Moonshot",
      "api_name": "kimi-k2.6",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_kimi-k2.6__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.46919333333333335,
          "normalized": 46.919333333333334,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "kimi-k2.6-thinking",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_kimi-k2.6__livebench_global_average__v1_11_27__v3_e1_2026_10_18_reattest",
          "raw_score": 0.7053878571428572,
          "normalized": 70.53878571428572,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "kimi-k2.6-thinking",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "MMMU-Pro: Artificial Analysis does not state the configuration it tested"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "mimo-v2-5-pro",
      "display_name": "MiMo V2.5 Pro",
      "position": 38,
      "state": "early_results",
      "rank": null,
      "provider": "Xiaomi",
      "api_name": "mimo-v2-5-pro",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_mimo-v2-5-pro__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0051,
          "normalized": 0.51,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "MiMo V2.5 Pro",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 0.51
          }
        },
        "livebench_agentic_coding": null,
        "arc_agi_2": null,
        "livebench_global_average": null,
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "livebench_agentic_coding"
        ],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_mimo-v2-5-pro__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.3411,
            "normalized": 34.11,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "MiMo V2.5 Pro",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "minimax-m2.7",
      "display_name": "MiniMax M2.7",
      "position": 39,
      "state": "early_results",
      "rank": null,
      "provider": "MiniMax",
      "api_name": "minimax-m2.7",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": null,
        "arc_agi_2": null,
        "livebench_global_average": null,
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "IDENTITY_UNRESOLVED"
          ],
          "line_code": "IDENTITY_UNRESOLVED",
          "line": "Terminal-Bench 4.0: the Vals entry is not confirmed to be this model"
        },
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "BENCHMARK_IDENTITY_NOT_PINNED",
            "AVAILABILITY_NOT_FOUND_IN_STATED_SCOPE",
            "RELEASE_SUPERSEDED",
            "VALUE_DERIVATION_NOT_ADMISSIBLE",
            "OTHER_LIVEBENCH_RELEASE",
            "NO_SOURCE_ROW_ANCHOR"
          ],
          "line_code": "BENCHMARK_IDENTITY_NOT_PINNED",
          "line": "LiveBench global average: the LiveBench result on record is for a different version of the test"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "livebench_agentic_coding",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "minimax-m3",
      "display_name": "MiniMax M3",
      "position": 40,
      "state": "early_results",
      "rank": null,
      "provider": "MiniMax",
      "api_name": "minimax-m3",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": {
          "evidence_id": "ev_minimax-m3__terminal_bench_4_0__v3_e1_2026_10_18",
          "raw_score": 0.0101,
          "normalized": 1.01,
          "value_derivation": "direct_read",
          "benchmark_identity": "vals/terminal-bench-4.0/mini-swe-agent",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Vals",
            "url": "https://www.vals.ai/benchmarks/terminal-bench-4",
            "row_label": "MiniMax-M3",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": 1.01
          }
        },
        "livebench_agentic_coding": {
          "evidence_id": "ev_minimax-m3__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.4065633333333333,
          "normalized": 40.65633333333333,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "minimax-m3",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_minimax-m3__livebench_global_average__v1_11_27__v3_e1_2026_10_18_reattest",
          "raw_score": 0.6725676190476189,
          "normalized": 67.25676190476189,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "minimax-m3",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "Humanity's Last Exam: Artificial Analysis does not state the configuration it tested"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "MMMU-Pro: Artificial Analysis does not state the configuration it tested"
        }
      ],
      "coding": {
        "score": 29.745444444444445,
        "rank": 25,
        "missing": [],
        "cells": {
          "vibe_code_bench_1_1": {
            "evidence_id": "ev_minimax-m3__vibe_code_bench_1_1__v3_2026_10_23",
            "raw_score": 0.4757,
            "normalized": 47.57,
            "value_derivation": "direct_read",
            "benchmark_identity": "vals/vibe-code-bench-1.1/openhands",
            "disposition": "admissible",
            "lifecycle": "current",
            "serving": {
              "capability": "not_material",
              "policy": "unspecified",
              "use": "not_applicable"
            },
            "mode": "standalone",
            "reason_codes": [],
            "serving_status": "standalone",
            "recount": null,
            "source": {
              "evaluator": "Vals",
              "url": "https://www.vals.ai/benchmarks/vibe-code",
              "row_label": "MiniMax-M3",
              "date": "2026-10-23",
              "date_kind": "read",
              "standard_error_pp": null
            }
          }
        }
      }
    },
    {
      "model_id": "muse-glimmer",
      "display_name": "Muse Glimmer",
      "position": 41,
      "state": "early_results",
      "rank": null,
      "provider": "Meta",
      "api_name": "muse-glimmer",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": null,
        "arc_agi_2": null,
        "livebench_global_average": null,
        "hle": {
          "evidence_id": "ev_muse-glimmer__hle",
          "raw_score": 0.219647822057461,
          "normalized": 21.9647822057461,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Muse Glimmer (high)",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "mmmu_pro": {
          "evidence_id": "ev_muse-glimmer__mmmu_pro__aa_2026_09_17",
          "raw_score": 0.743352601156069,
          "normalized": 74.3352601156069,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/mmmu-pro/mc10-pass-at-1",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/mmmu-pro",
            "row_label": "Muse Glimmer (high)",
            "date": "2026-09-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        }
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NO_EVALUATOR_IDENTITY"
          ],
          "line_code": "NO_EVALUATOR_IDENTITY",
          "line": "Terminal-Bench 4.0: no Vals entry is matched to this model"
        },
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "livebench_agentic_coding",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "muse-spark",
      "display_name": "Muse Spark",
      "position": 42,
      "state": "early_results",
      "rank": null,
      "provider": "Meta",
      "api_name": "muse-spark",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": null,
        "arc_agi_2": null,
        "livebench_global_average": null,
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "ARC-AGI-2: the ARC Prize result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "BENCHMARK_IDENTITY_NOT_PINNED",
            "AVAILABILITY_NOT_FOUND_IN_STATED_SCOPE",
            "RELEASE_SUPERSEDED",
            "VALUE_DERIVATION_NOT_ADMISSIBLE",
            "OTHER_LIVEBENCH_RELEASE",
            "NO_SOURCE_ROW_ANCHOR"
          ],
          "line_code": "BENCHMARK_IDENTITY_NOT_PINNED",
          "line": "LiveBench global average: the LiveBench result on record is for a different version of the test"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "MMMU-Pro: Artificial Analysis does not state the configuration it tested"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "livebench_agentic_coding",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "muse-spark-1.1",
      "display_name": "Muse Spark 1.1",
      "position": 43,
      "state": "early_results",
      "rank": null,
      "provider": "Meta",
      "api_name": "muse-spark-1.1",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_muse-spark-1.1__livebench_agentic_coding__v296_2026_10_18",
          "raw_score": 0.5853533333333334,
          "normalized": 58.53533333333334,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "muse-spark-1.1-xhigh",
            "date": "2026-10-18",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_muse-spark-1.1__livebench_global_average__refresh_2026_08_12",
          "raw_score": 0.752995,
          "normalized": 75.2995,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai",
            "row_label": "muse-spark-1.1-xhigh",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_muse-spark-1.1__hle__v293_2026_09_26",
          "raw_score": 0.462001853568119,
          "normalized": 46.2001853568119,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Muse Spark 1.1 (xhigh)",
            "date": "2026-09-26",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "muse-wonder",
      "display_name": "Muse Wonder",
      "position": 44,
      "state": "early_results",
      "rank": null,
      "provider": "Meta",
      "api_name": "muse-wonder",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_muse-wonder__livebench_agentic_coding__v3_candidate_2026_10_25",
          "raw_score": 0.6272733333333335,
          "normalized": 62.72733333333335,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "muse-wonder-1.0-max",
            "date": "2026-10-25",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_muse-wonder__livebench_global_average__v3_candidate_2026_10_25",
          "raw_score": 0.8115589285714284,
          "normalized": 81.15589285714285,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "muse-wonder-1.0-max",
            "date": "2026-10-25",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": {
          "evidence_id": "ev_muse-wonder__hle__v3_candidate_2026_10_25",
          "raw_score": 0.500926784059314,
          "normalized": 50.0926784059314,
          "value_derivation": "direct_read",
          "benchmark_identity": "artificial-analysis/hle/text-only-2158",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "Artificial Analysis",
            "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam",
            "row_label": "Muse Wonder (Max)",
            "date": "2026-10-25",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "IDENTITY_UNRESOLVED"
          ],
          "line_code": "IDENTITY_UNRESOLVED",
          "line": "Terminal-Bench 4.0: the Vals entry is not confirmed to be this model"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "nemotron-3-ultra",
      "display_name": "Nemotron 3 Ultra",
      "position": 45,
      "state": "early_results",
      "rank": null,
      "provider": "NVIDIA",
      "api_name": "nvidia-nemotron-3-ultra-550b-a55b",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": null,
        "arc_agi_2": null,
        "livebench_global_average": null,
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "livebench_agentic_coding",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench Agentic Coding: no LiveBench result on record"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "livebench_global_average",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "LiveBench global average: no LiveBench result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "CONFIGURATION_UNRESOLVED"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "Humanity's Last Exam: Artificial Analysis does not state the configuration it tested"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "livebench_agentic_coding",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "qwen-3-7-max",
      "display_name": "Qwen 3.7 Max",
      "position": 46,
      "state": "early_results",
      "rank": null,
      "provider": "Alibaba",
      "api_name": "qwen-3-7-max",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_qwen-3-7-max__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.4358600000000001,
          "normalized": 43.586000000000006,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "qwen3.7-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_qwen-3-7-max__livebench_global_average__v1_11_27__v3_e1_2026_10_18_reattest",
          "raw_score": 0.7313660714285714,
          "normalized": 73.13660714285713,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "qwen3.7-max",
            "date": "2026-10-17",
            "date_kind": "read",
            "standard_error_pp": null
          }
        },
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "NOT_YET_TESTED_BY_EVALUATOR"
          ],
          "line_code": "NOT_YET_TESTED_BY_EVALUATOR",
          "line": "Terminal-Bench 4.0: not yet tested by Vals"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "NOT_ASSESSED_FOR_V3",
          "line": "Humanity's Last Exam: the Artificial Analysis result on record has not yet passed the v3 evidence check"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "MMMU-Pro: no Artificial Analysis result on record"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    },
    {
      "model_id": "qwen-3-8-max",
      "display_name": "Qwen 3.8 Max",
      "position": 47,
      "state": "early_results",
      "rank": null,
      "provider": "Alibaba",
      "api_name": "qwen-3-8-max",
      "held": false,
      "hold_code": null,
      "hold_line": null,
      "score_label": null,
      "official_score": null,
      "minimum_score": null,
      "serving_label": null,
      "cells": {
        "terminal_bench_4_0": null,
        "livebench_agentic_coding": {
          "evidence_id": "ev_qwen-3-8-max__livebench_agentic_coding__2026_08_22",
          "raw_score": 0.6464666666666666,
          "normalized": 64.64666666666666,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/agentic-coding-task-mean",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "qwen3.8-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "arc_agi_2": null,
        "livebench_global_average": {
          "evidence_id": "ev_qwen-3-8-max__livebench_global_average__2026_08_22",
          "raw_score": 0.7846089285714286,
          "normalized": 78.46089285714287,
          "value_derivation": "evaluator_formula_from_published_components",
          "benchmark_identity": "livebench/2026-06-25/global-average",
          "disposition": "admissible",
          "lifecycle": "current",
          "serving": {
            "capability": "not_material",
            "policy": "unspecified",
            "use": "not_applicable"
          },
          "mode": "standalone",
          "reason_codes": [],
          "serving_status": "standalone",
          "recount": null,
          "source": {
            "evaluator": "LiveBench",
            "url": "https://livebench.ai/",
            "row_label": "qwen3.8-max",
            "date": null,
            "date_kind": null,
            "standard_error_pp": null
          }
        },
        "hle": null,
        "mmmu_pro": null
      },
      "missing": [
        {
          "benchmark_id": "terminal_bench_4_0",
          "codes": [
            "CHECKPOINT_UNRESOLVED"
          ],
          "line_code": "CHECKPOINT_UNRESOLVED",
          "line": "Terminal-Bench 4.0: Vals does not state which checkpoint of the model it tested"
        },
        {
          "benchmark_id": "arc_agi_2",
          "codes": [
            "NOT_IN_LEDGER"
          ],
          "line_code": "NOT_IN_LEDGER",
          "line": "ARC-AGI-2: no ARC Prize result on record"
        },
        {
          "benchmark_id": "hle",
          "codes": [
            "CONFIGURATION_UNRESOLVED",
            "NOT_ASSESSED_FOR_V3"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "Humanity's Last Exam: Artificial Analysis does not state the configuration it tested"
        },
        {
          "benchmark_id": "mmmu_pro",
          "codes": [
            "CONFIGURATION_UNRESOLVED"
          ],
          "line_code": "CONFIGURATION_UNRESOLVED",
          "line": "MMMU-Pro: Artificial Analysis does not state the configuration it tested"
        }
      ],
      "coding": {
        "score": null,
        "rank": null,
        "missing": [
          "terminal_bench_4_0",
          "vibe_code_bench_1_1"
        ],
        "cells": {
          "vibe_code_bench_1_1": null
        }
      }
    }
  ],
  "guard": {
    "official_totals": 13,
    "required_cells_scored": 78,
    "proven_minimums": 17,
    "minimum_cells_used": 78,
    "cells_checked": 189,
    "derived_values_scored": 0,
    "labelled_cells_scored": 14,
    "coding_tab": {
      "coding_scores": 27,
      "coding_cells_checked": 31,
      "derived_values_scored": 0
    }
  }
}