{
  "catalogVersion": "4510bd969166c4aba5fab0e6303d728328ea2ea027158d72b26b3ec40ce75586",
  "scoringVersion": "4153043dfc8f41cad6c9de84ce95493fa262f59d1864e0f7aec3e369949043bc",
  "asOf": "2026-11-21",
  "metrics": [
    {
      "id": "coding",
      "label": "Coding",
      "short": "Terminal-Bench 4.1",
      "seriesId": "terminal-bench-4-1-models",
      "cohort": {
        "id": "terminal-bench-4-1-models-2026-11-19",
        "title": "Terminal-Bench",
        "version": "4.1",
        "unit": "percentage points",
        "conditions": "Best public leaderboard resolution rate for each model in any agent harness. The agent and effort behind the score are named with it.",
        "sourceId": "terminal-bench",
        "measuredAt": "2026-11-19",
        "verifiedAt": "2026-11-19"
      },
      "ranked": [
        {
          "id": "claude-fable-5-2",
          "name": "Claude Fable 5.2",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 65.76,
          "configuration": "Claude Code · max",
          "detail": "±2.9 (95% CI), 330 trials, submitted 2026-11-09"
        },
        {
          "id": "claude-opus-5-5",
          "name": "Claude Opus 5.5",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 65.76,
          "configuration": "Claude Code · max",
          "detail": "±3.1 (95% CI), 330 trials, submitted 2026-09-22"
        },
        {
          "id": "gemini-4-carbon",
          "name": "Gemini 4 Carbon",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini 4 Carbon documentation",
                  "url": "https://aistudio.google.com/docs/models/gemini-4-carbon"
                }
              }
            }
          ],
          "unverified": [],
          "score": 64.55,
          "configuration": "Antigravity CLI · high",
          "detail": "±3.2 (95% CI), 330 trials, submitted 2026-10-28"
        },
        {
          "id": "claude-sonnet-5-5",
          "name": "Claude Sonnet 5.5",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 63.94,
          "configuration": "Claude Code · max",
          "detail": "±3.0 (95% CI), 330 trials, submitted 2026-09-28"
        },
        {
          "id": "gpt-6-2-astra",
          "name": "GPT-6.2 Astra",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI models overview",
                  "url": "https://developers.openai.com/api/docs/models"
                }
              }
            }
          ],
          "unverified": [],
          "score": 62.12,
          "configuration": "Codex · max",
          "detail": "±2.3 (95% CI), 330 trials, submitted 2026-11-17"
        },
        {
          "id": "gpt-6-2-sol",
          "name": "GPT-6.2 Sol",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI models overview",
                  "url": "https://developers.openai.com/api/docs/models"
                }
              }
            }
          ],
          "unverified": [],
          "score": 61.52,
          "configuration": "Codex · max",
          "detail": "±2.8 (95% CI), 330 trials, submitted 2026-11-17"
        },
        {
          "id": "gemini-4-hydrogen",
          "name": "Gemini 4 Hydrogen",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini 4 Hydrogen documentation",
                  "url": "https://aistudio.google.com/docs/models/gemini-4-hydrogen"
                }
              }
            }
          ],
          "unverified": [],
          "score": 56.36,
          "configuration": "Antigravity CLI · high",
          "detail": "±3.0 (95% CI), 330 trials, submitted 2026-11-12"
        },
        {
          "id": "gemini-4-argon",
          "name": "Gemini 4 Argon",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini 4 Argon documentation",
                  "url": "https://aistudio.google.com/docs/models/gemini-4-argon"
                }
              }
            }
          ],
          "unverified": [],
          "score": 55.45,
          "configuration": "Antigravity CLI · high",
          "detail": "±2.9 (95% CI), 330 trials, submitted 2026-09-30"
        },
        {
          "id": "gpt-6-1-terra",
          "name": "GPT-6.1 Terra",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI model docs",
                  "url": "https://developers.openai.com/api/docs/models/gpt-6.1-terra"
                }
              }
            }
          ],
          "unverified": [],
          "score": 53.33,
          "configuration": "Codex · max",
          "detail": "±3.1 (95% CI), 330 trials, submitted 2026-10-26"
        },
        {
          "id": "claude-haiku-5-5",
          "name": "Claude Haiku 5.5",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 40,
          "configuration": "Claude Code · max",
          "detail": "±3.6 (95% CI), 330 trials, submitted 2026-10-07"
        },
        {
          "id": "grok-4-7",
          "name": "Grok 4.7",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 38.79,
          "configuration": "Grok Build · xhigh",
          "detail": "±3.6 (95% CI), 330 trials, submitted 2026-09-21"
        },
        {
          "id": "deepseek-v4-1-flash",
          "name": "DeepSeek V4.1 Flash",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 38.48,
          "configuration": "Claude Code · max",
          "detail": "±3.8 (95% CI), 330 trials, submitted 2026-10-17"
        },
        {
          "id": "mistral-large-4",
          "name": "Mistral Large 4",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 27.58,
          "configuration": "Claude Code · max",
          "detail": "±3.9 (95% CI), 330 trials, submitted 2026-10-06"
        },
        {
          "id": "qwen3-8-max-0902",
          "name": "Qwen3.8 Max (0902)",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 26.97,
          "configuration": "Claude Code · max",
          "detail": "±3.9 (95% CI), 330 trials, submitted 2026-09-02"
        },
        {
          "id": "gpt-5-6-terra",
          "name": "GPT-5.6 Terra",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 21.52,
          "configuration": "Codex · max",
          "detail": "±3.3 (95% CI), 330 trials, submitted 2026-06-26"
        },
        {
          "id": "gemini-3-8-flash",
          "name": "Gemini 3.8 Flash",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini model docs",
                  "url": "https://aistudio.google.com/docs/models/gemini-3.8-flash"
                }
              }
            }
          ],
          "unverified": [],
          "score": 18.18,
          "configuration": "mini-SWE-agent · high",
          "detail": "±3.4 (95% CI), 330 trials, submitted 2026-09-02"
        },
        {
          "id": "gpt-6-luna",
          "name": "GPT-6 Luna",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI models overview",
                  "url": "https://developers.openai.com/api/docs/models"
                }
              }
            }
          ],
          "unverified": [],
          "score": 15.15,
          "configuration": "Codex · max",
          "detail": "±2.7 (95% CI), 330 trials, submitted 2026-09-22"
        },
        {
          "id": "deepseek-v4-pro",
          "name": "DeepSeek V4 Pro",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 6.67,
          "configuration": "Claude Code · max",
          "detail": "±2.5 (95% CI), 330 trials, submitted 2026-08-13"
        }
      ],
      "unranked": [
        {
          "id": "claude-sonnet-4-6",
          "name": "Claude Sonnet 4.6",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "llama-4-maverick",
          "name": "Llama 4 Maverick",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "llama-4-scout",
          "name": "Llama 4 Scout",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "qwen3-14b",
          "name": "Qwen3-14B",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "qwen3-32b",
          "name": "Qwen3-32B",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "qwen3-8-27b",
          "name": "Qwen3.8 27B",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        }
      ]
    },
    {
      "id": "overall",
      "label": "Overall",
      "short": "AA Intelligence Index",
      "seriesId": "aa-intelligence-index-v5",
      "cohort": {
        "id": "aa-intelligence-index-v5-2026-11-19",
        "title": "Artificial Analysis Intelligence Index",
        "version": "v5",
        "unit": "index points",
        "conditions": "Independent evaluation by Artificial Analysis on its standard harness, each model at the configuration named with its score.",
        "sourceId": "artificial-analysis",
        "measuredAt": "2026-11-19",
        "verifiedAt": "2026-11-19"
      },
      "ranked": [
        {
          "id": "claude-fable-5-2",
          "name": "Claude Fable 5.2",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 64.6,
          "configuration": "Claude Fable 5.2 (Max, Default Fallback)"
        },
        {
          "id": "gpt-6-2-astra",
          "name": "GPT-6.2 Astra",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI models overview",
                  "url": "https://developers.openai.com/api/docs/models"
                }
              }
            }
          ],
          "unverified": [],
          "score": 62.1,
          "configuration": "GPT-6.2 Astra (Max)"
        },
        {
          "id": "gemini-4-carbon",
          "name": "Gemini 4 Carbon",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini 4 Carbon documentation",
                  "url": "https://aistudio.google.com/docs/models/gemini-4-carbon"
                }
              }
            }
          ],
          "unverified": [],
          "score": 60,
          "configuration": "Gemini 4 Carbon (High)"
        },
        {
          "id": "claude-opus-5-5",
          "name": "Claude Opus 5.5",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 59.1,
          "configuration": "Claude Opus 5.5 (Max, Default Fallback)"
        },
        {
          "id": "gpt-6-2-sol",
          "name": "GPT-6.2 Sol",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI models overview",
                  "url": "https://developers.openai.com/api/docs/models"
                }
              }
            }
          ],
          "unverified": [],
          "score": 57.3,
          "configuration": "GPT-6.2 Sol (Max)"
        },
        {
          "id": "claude-sonnet-5-5",
          "name": "Claude Sonnet 5.5",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 54.5,
          "configuration": "Claude Sonnet 5.5 (Max, Default Fallback)"
        },
        {
          "id": "gemini-4-hydrogen",
          "name": "Gemini 4 Hydrogen",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini 4 Hydrogen documentation",
                  "url": "https://aistudio.google.com/docs/models/gemini-4-hydrogen"
                }
              }
            }
          ],
          "unverified": [],
          "score": 53.9,
          "configuration": "Gemini 4 Hydrogen (Xhigh)"
        },
        {
          "id": "gpt-6-1-terra",
          "name": "GPT-6.1 Terra",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI model docs",
                  "url": "https://developers.openai.com/api/docs/models/gpt-6.1-terra"
                }
              }
            }
          ],
          "unverified": [],
          "score": 51.3,
          "configuration": "GPT-6.1 Terra (Max)"
        },
        {
          "id": "gemini-4-argon",
          "name": "Gemini 4 Argon",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini 4 Argon documentation",
                  "url": "https://aistudio.google.com/docs/models/gemini-4-argon"
                }
              }
            }
          ],
          "unverified": [],
          "score": 50.4,
          "configuration": "Gemini 4 Argon (High)"
        },
        {
          "id": "claude-haiku-5-5",
          "name": "Claude Haiku 5.5",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 36.5,
          "configuration": "Claude Haiku 5.5 (Max)"
        },
        {
          "id": "grok-4-7",
          "name": "Grok 4.7",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 35.5,
          "configuration": "Grok 4.7 (Xhigh)"
        },
        {
          "id": "qwen3-8-max-0902",
          "name": "Qwen3.8 Max (0902)",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 33.7,
          "configuration": "Qwen3.8 Max (0902)"
        },
        {
          "id": "deepseek-v4-1-flash",
          "name": "DeepSeek V4.1 Flash",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 32.6,
          "configuration": "DeepSeek V4.1 Flash 1017 (Max)"
        },
        {
          "id": "gpt-5-6-terra",
          "name": "GPT-5.6 Terra",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 32.3,
          "configuration": "GPT-5.6 Terra (Max)"
        },
        {
          "id": "gemini-3-8-flash",
          "name": "Gemini 3.8 Flash",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "Gemini model docs",
                  "url": "https://aistudio.google.com/docs/models/gemini-3.8-flash"
                }
              }
            }
          ],
          "unverified": [],
          "score": 30.8,
          "configuration": "Gemini 3.8 Flash (High)"
        },
        {
          "id": "gpt-6-luna",
          "name": "GPT-6 Luna",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": true,
              "evidence": {
                "value": true,
                "status": "verified",
                "verifiedAt": "2026-11-18",
                "source": {
                  "name": "OpenAI models overview",
                  "url": "https://developers.openai.com/api/docs/models"
                }
              }
            }
          ],
          "unverified": [],
          "score": 27.9,
          "configuration": "GPT-6 Luna (Max)"
        },
        {
          "id": "mistral-large-4",
          "name": "Mistral Large 4",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 26.1,
          "configuration": "Mistral Large 4 (High)"
        },
        {
          "id": "deepseek-v4-pro",
          "name": "DeepSeek V4 Pro",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 23.1,
          "configuration": "DeepSeek V4 Pro 0813 (Max)"
        },
        {
          "id": "qwen3-8-27b",
          "name": "Qwen3.8 27B",
          "status": "ranked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": 20.1,
          "configuration": "Qwen3.8 27B (Xhigh)"
        }
      ],
      "unranked": [
        {
          "id": "claude-sonnet-4-6",
          "name": "Claude Sonnet 4.6",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "llama-4-maverick",
          "name": "Llama 4 Maverick",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "llama-4-scout",
          "name": "Llama 4 Scout",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "qwen3-14b",
          "name": "Qwen3-14B",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        },
        {
          "id": "qwen3-32b",
          "name": "Qwen3-32B",
          "status": "not-benchmarked",
          "constraints": [
            {
              "attribute": "tools",
              "equals": true,
              "match": null,
              "evidence": {
                "value": null,
                "status": "unknown"
              }
            }
          ],
          "unverified": [
            "tools"
          ],
          "score": null
        }
      ]
    }
  ],
  "ranked": [
    {
      "id": "claude-fable-5-2",
      "name": "Claude Fable 5.2",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 65.76,
      "configuration": "Claude Code · max",
      "detail": "±2.9 (95% CI), 330 trials, submitted 2026-11-09"
    },
    {
      "id": "claude-opus-5-5",
      "name": "Claude Opus 5.5",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 65.76,
      "configuration": "Claude Code · max",
      "detail": "±3.1 (95% CI), 330 trials, submitted 2026-09-22"
    },
    {
      "id": "gemini-4-carbon",
      "name": "Gemini 4 Carbon",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "Gemini 4 Carbon documentation",
              "url": "https://aistudio.google.com/docs/models/gemini-4-carbon"
            }
          }
        }
      ],
      "unverified": [],
      "score": 64.55,
      "configuration": "Antigravity CLI · high",
      "detail": "±3.2 (95% CI), 330 trials, submitted 2026-10-28"
    },
    {
      "id": "claude-sonnet-5-5",
      "name": "Claude Sonnet 5.5",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 63.94,
      "configuration": "Claude Code · max",
      "detail": "±3.0 (95% CI), 330 trials, submitted 2026-09-28"
    },
    {
      "id": "gpt-6-2-astra",
      "name": "GPT-6.2 Astra",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "OpenAI models overview",
              "url": "https://developers.openai.com/api/docs/models"
            }
          }
        }
      ],
      "unverified": [],
      "score": 62.12,
      "configuration": "Codex · max",
      "detail": "±2.3 (95% CI), 330 trials, submitted 2026-11-17"
    },
    {
      "id": "gpt-6-2-sol",
      "name": "GPT-6.2 Sol",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "OpenAI models overview",
              "url": "https://developers.openai.com/api/docs/models"
            }
          }
        }
      ],
      "unverified": [],
      "score": 61.52,
      "configuration": "Codex · max",
      "detail": "±2.8 (95% CI), 330 trials, submitted 2026-11-17"
    },
    {
      "id": "gemini-4-hydrogen",
      "name": "Gemini 4 Hydrogen",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "Gemini 4 Hydrogen documentation",
              "url": "https://aistudio.google.com/docs/models/gemini-4-hydrogen"
            }
          }
        }
      ],
      "unverified": [],
      "score": 56.36,
      "configuration": "Antigravity CLI · high",
      "detail": "±3.0 (95% CI), 330 trials, submitted 2026-11-12"
    },
    {
      "id": "gemini-4-argon",
      "name": "Gemini 4 Argon",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "Gemini 4 Argon documentation",
              "url": "https://aistudio.google.com/docs/models/gemini-4-argon"
            }
          }
        }
      ],
      "unverified": [],
      "score": 55.45,
      "configuration": "Antigravity CLI · high",
      "detail": "±2.9 (95% CI), 330 trials, submitted 2026-09-30"
    },
    {
      "id": "gpt-6-1-terra",
      "name": "GPT-6.1 Terra",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "OpenAI model docs",
              "url": "https://developers.openai.com/api/docs/models/gpt-6.1-terra"
            }
          }
        }
      ],
      "unverified": [],
      "score": 53.33,
      "configuration": "Codex · max",
      "detail": "±3.1 (95% CI), 330 trials, submitted 2026-10-26"
    },
    {
      "id": "claude-haiku-5-5",
      "name": "Claude Haiku 5.5",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 40,
      "configuration": "Claude Code · max",
      "detail": "±3.6 (95% CI), 330 trials, submitted 2026-10-07"
    },
    {
      "id": "grok-4-7",
      "name": "Grok 4.7",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 38.79,
      "configuration": "Grok Build · xhigh",
      "detail": "±3.6 (95% CI), 330 trials, submitted 2026-09-21"
    },
    {
      "id": "deepseek-v4-1-flash",
      "name": "DeepSeek V4.1 Flash",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 38.48,
      "configuration": "Claude Code · max",
      "detail": "±3.8 (95% CI), 330 trials, submitted 2026-10-17"
    },
    {
      "id": "mistral-large-4",
      "name": "Mistral Large 4",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 27.58,
      "configuration": "Claude Code · max",
      "detail": "±3.9 (95% CI), 330 trials, submitted 2026-10-06"
    },
    {
      "id": "qwen3-8-max-0902",
      "name": "Qwen3.8 Max (0902)",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 26.97,
      "configuration": "Claude Code · max",
      "detail": "±3.9 (95% CI), 330 trials, submitted 2026-09-02"
    },
    {
      "id": "gpt-5-6-terra",
      "name": "GPT-5.6 Terra",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 21.52,
      "configuration": "Codex · max",
      "detail": "±3.3 (95% CI), 330 trials, submitted 2026-06-26"
    },
    {
      "id": "gemini-3-8-flash",
      "name": "Gemini 3.8 Flash",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "Gemini model docs",
              "url": "https://aistudio.google.com/docs/models/gemini-3.8-flash"
            }
          }
        }
      ],
      "unverified": [],
      "score": 18.18,
      "configuration": "mini-SWE-agent · high",
      "detail": "±3.4 (95% CI), 330 trials, submitted 2026-09-02"
    },
    {
      "id": "gpt-6-luna",
      "name": "GPT-6 Luna",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": true,
          "evidence": {
            "value": true,
            "status": "verified",
            "verifiedAt": "2026-11-18",
            "source": {
              "name": "OpenAI models overview",
              "url": "https://developers.openai.com/api/docs/models"
            }
          }
        }
      ],
      "unverified": [],
      "score": 15.15,
      "configuration": "Codex · max",
      "detail": "±2.7 (95% CI), 330 trials, submitted 2026-09-22"
    },
    {
      "id": "deepseek-v4-pro",
      "name": "DeepSeek V4 Pro",
      "status": "ranked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": 6.67,
      "configuration": "Claude Code · max",
      "detail": "±2.5 (95% CI), 330 trials, submitted 2026-08-13"
    }
  ],
  "unranked": [
    {
      "id": "claude-sonnet-4-6",
      "name": "Claude Sonnet 4.6",
      "status": "not-benchmarked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": null
    },
    {
      "id": "llama-4-maverick",
      "name": "Llama 4 Maverick",
      "status": "not-benchmarked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": null
    },
    {
      "id": "llama-4-scout",
      "name": "Llama 4 Scout",
      "status": "not-benchmarked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": null
    },
    {
      "id": "qwen3-14b",
      "name": "Qwen3-14B",
      "status": "not-benchmarked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": null
    },
    {
      "id": "qwen3-32b",
      "name": "Qwen3-32B",
      "status": "not-benchmarked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": null
    },
    {
      "id": "qwen3-8-27b",
      "name": "Qwen3.8 27B",
      "status": "not-benchmarked",
      "constraints": [
        {
          "attribute": "tools",
          "equals": true,
          "match": null,
          "evidence": {
            "value": null,
            "status": "unknown"
          }
        }
      ],
      "unverified": [
        "tools"
      ],
      "score": null
    }
  ],
  "configuration": {
    "title": "Model benchmark ranking",
    "description": "Models ranked by independent benchmark score. Coding uses each model's best Terminal-Bench result in any agent; Overall uses the Artificial Analysis Intelligence Index at each model's highest-effort configuration. Models documented as lacking function calling are excluded; models whose function-calling support is not yet recorded are ranked and marked unverified. Models without a current score are listed as not benchmarked.",
    "category": "models",
    "requires": [
      {
        "attribute": "tools",
        "equals": true
      }
    ],
    "metrics": [
      {
        "id": "coding",
        "label": "Coding",
        "short": "Terminal-Bench 4.1",
        "seriesId": "terminal-bench-4-1-models"
      },
      {
        "id": "overall",
        "label": "Overall",
        "short": "AA Intelligence Index",
        "seriesId": "aa-intelligence-index-v5"
      }
    ],
    "version": "4153043dfc8f41cad6c9de84ce95493fa262f59d1864e0f7aec3e369949043bc"
  },
  "url": "/api/ranking.json"
}