{
  "data": {
    "area": "agent-tasks",
    "attribution": "Terminal-Bench, Stanford and the Laude Institute, Apache 2.0",
    "cadence": "as models are released",
    "categories": [
      "inference",
      "open-weights",
      "agent-harnesses"
    ],
    "ceiling": 100,
    "competitor": "",
    "data": "https://github.com/harbor-framework/terminal-bench/tree/main/leaderboard/submissions",
    "direction": "higher",
    "floor": 0,
    "json": "https://www.anchorterminal.com/benchmarks/terminal-bench/index.json",
    "licence": "Apache-2.0",
    "licenceUrl": "https://github.com/harbor-framework/terminal-bench/blob/main/LICENSE",
    "measures": "An agent harness running a model in a sandboxed shell, five trials or more on every task, until the task's tests pass. A row is one harness and model pair at one reasoning effort; the model is what's ranked.",
    "method": "https://www.tbench.ai/",
    "models": 33,
    "name": "Terminal-Bench",
    "newest": "2026-11-20",
    "page": "https://www.anchorterminal.com/benchmarks/terminal-bench/",
    "read": "2026-11-20",
    "results": 51,
    "runBy": "Stanford and the Laude Institute (the Terminal-Bench maintainers)",
    "saturated": false,
    "slug": "terminal-bench",
    "status": "current",
    "unit": "% of trials passed",
    "versions": [
      {
        "rows": [
          {
            "as": "anthropic/claude-opus-5-5",
            "ci": [
              61.74,
              67.96
            ],
            "date": "2026-09-30",
            "listing": "anthropic-api",
            "model": "claude-opus-5-5",
            "name": "Claude Opus 5.5",
            "of": 26,
            "rank": 1,
            "runBy": "Terminal-Bench maintainers",
            "score": 64.85,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.284",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "anthropic/claude-sonnet-5-5",
            "ci": [
              58.88,
              64.76
            ],
            "date": "2026-09-30",
            "listing": "anthropic-api",
            "model": "claude-sonnet-5-5",
            "name": "Claude Sonnet 5.5",
            "of": 26,
            "rank": 2,
            "runBy": "Terminal-Bench maintainers",
            "score": 61.82,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.284",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Kimi K3.1 Pro",
            "ci": [
              56.8,
              65.02
            ],
            "date": "2026-10-30",
            "listing": "kimi-k3-1-pro",
            "model": "kimi-k3-1-pro",
            "name": "Kimi K3.1 Pro",
            "of": 26,
            "rank": 3,
            "runBy": "Terminal-Bench maintainers",
            "score": 60.91,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GPT-6.1 Sol",
            "ci": [
              55.07,
              61.29
            ],
            "date": "2026-09-30",
            "listing": "openai-api",
            "model": "gpt-6-1-sol",
            "name": "GPT-6.1 Sol",
            "of": 26,
            "rank": 4,
            "runBy": "Terminal-Bench maintainers",
            "score": 58.18,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.159.0",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "anthropic/claude-fable-5-1",
            "ci": [
              54.12,
              61.64
            ],
            "date": "2026-09-02",
            "listing": "anthropic-api",
            "model": "claude-fable-5-1",
            "name": "Claude Fable 5.1",
            "of": 26,
            "rank": 5,
            "runBy": "Terminal-Bench maintainers",
            "score": 57.88,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.257",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Gemini 4 Argon",
            "ci": [
              51.88,
              57.82
            ],
            "date": "2026-11-13",
            "listing": "gemini-4-argon",
            "model": "gemini-4-argon",
            "name": "Gemini 4 Argon",
            "of": 26,
            "rank": 6,
            "runBy": "Terminal-Bench maintainers",
            "score": 54.85,
            "setting": {
              "effort": "high",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.2",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GPT-6.1 Terra",
            "ci": [
              49,
              54.64
            ],
            "date": "2026-10-28",
            "listing": "openai-api",
            "model": "gpt-6-1-terra",
            "name": "GPT-6.1 Terra",
            "of": 26,
            "rank": 7,
            "runBy": "Terminal-Bench maintainers",
            "score": 51.82,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.164.0",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GPT-6 Sol",
            "ci": [
              46.16,
              52.62
            ],
            "date": "2026-09-30",
            "listing": "azure-openai",
            "model": "gpt-6-sol",
            "name": "GPT-6 Sol",
            "of": 26,
            "rank": 8,
            "runBy": "Terminal-Bench maintainers",
            "score": 49.39,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.159.0",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Muse Wonder",
            "ci": [
              43.19,
              50.75
            ],
            "date": "2026-11-05",
            "listing": "meta-model-api",
            "model": "muse-wonder",
            "name": "Muse Wonder",
            "of": 26,
            "rank": 9,
            "runBy": "Terminal-Bench maintainers",
            "score": 46.97,
            "setting": {
              "effort": "xhigh",
              "harness": "Muse Code",
              "harnessListing": "muse-code",
              "harnessVersion": "1.4.14",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GLM-5.3",
            "ci": [
              38.59,
              45.05
            ],
            "date": "2026-08-26",
            "listing": "glm-5-3",
            "model": "glm-5-3",
            "name": "GLM-5.3",
            "of": 26,
            "rank": 10,
            "runBy": "Terminal-Bench maintainers",
            "score": 41.82,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.207",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "anthropic/claude-haiku-5-5",
            "ci": [
              36.31,
              43.69
            ],
            "date": "2026-11-06",
            "listing": "anthropic-api",
            "model": "claude-haiku-5-5",
            "name": "Claude Haiku 5.5",
            "of": 26,
            "rank": 11,
            "runBy": "Terminal-Bench maintainers",
            "score": 40,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "DeepSeek V4.1 Flash 1017",
            "ci": [
              36.27,
              43.73
            ],
            "date": "2026-10-31",
            "listing": "deepseek-v4-1-flash",
            "model": "deepseek-v4-1-flash",
            "name": "DeepSeek V4.1 Flash",
            "of": 26,
            "rank": 11,
            "runBy": "Terminal-Bench maintainers",
            "score": 40,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Hy4",
            "ci": [
              35.6,
              42.58
            ],
            "date": "2026-11-10",
            "listing": "hy4",
            "model": "hy4",
            "name": "Tencent Hy4",
            "of": 26,
            "rank": 13,
            "runBy": "Terminal-Bench maintainers",
            "score": 39.09,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GLM-5.3-Flash",
            "ci": [
              33.01,
              40.33
            ],
            "date": "2026-11-02",
            "listing": "glm-5-3-flash",
            "model": "glm-5-3-flash",
            "name": "GLM-5.3-Flash",
            "of": 26,
            "rank": 14,
            "runBy": "Terminal-Bench maintainers",
            "score": 36.67,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GLM-5.3-Flash",
            "ci": [
              32.22,
              39.3
            ],
            "date": "2026-10-06",
            "listing": "glm-5-3-flash",
            "model": "glm-5-3-flash",
            "name": "GLM-5.3-Flash",
            "runBy": "Terminal-Bench maintainers",
            "score": 35.76,
            "setting": {
              "effort": "none",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.285",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Mistral Large 4",
            "ci": [
              23.96,
              31.8
            ],
            "date": "2026-11-04",
            "listing": "mistral-large-4",
            "model": "mistral-large-4",
            "name": "Mistral Large 4",
            "of": 26,
            "rank": 15,
            "runBy": "Terminal-Bench maintainers",
            "score": 27.88,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Kimi K3",
            "ci": [
              18.62,
              26.22
            ],
            "date": "2026-11-10",
            "listing": "kimi-k3",
            "model": "kimi-k3",
            "name": "Kimi K3",
            "of": 26,
            "rank": 16,
            "runBy": "Terminal-Bench maintainers",
            "score": 22.42,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Gemini 3.8 Flash",
            "ci": [
              15.73,
              22.45
            ],
            "date": "2026-09-01",
            "listing": "vertex-ai",
            "model": "gemini-3-8-flash",
            "name": "Gemini 3.8 Flash",
            "of": 26,
            "rank": 17,
            "runBy": "Terminal-Bench maintainers",
            "score": 19.09,
            "setting": {
              "effort": "high",
              "harness": "mini-SWE-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "GPT-6 Luna",
            "ci": [
              13.64,
              19.08
            ],
            "date": "2026-09-30",
            "listing": "azure-openai",
            "model": "gpt-6-luna",
            "name": "GPT-6 Luna",
            "of": 26,
            "rank": 18,
            "runBy": "Terminal-Bench maintainers",
            "score": 16.36,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.159.0",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Muse Spark 1.3",
            "ci": [
              11.61,
              17.49
            ],
            "date": "2026-09-30",
            "listing": "meta-model-api",
            "model": "muse-spark-1-3",
            "name": "Muse Spark 1.3",
            "of": 26,
            "rank": 19,
            "runBy": "Terminal-Bench maintainers",
            "score": 14.55,
            "setting": {
              "effort": "xhigh",
              "harness": "Muse Code",
              "harnessListing": "muse-code",
              "harnessVersion": "1.4.1",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "MiniMax M3",
            "ci": [
              4.58,
              9.96
            ],
            "date": "2026-11-10",
            "listing": "minimax-api",
            "model": "minimax-m3",
            "name": "MiniMax M3",
            "of": 26,
            "rank": 20,
            "runBy": "Terminal-Bench maintainers",
            "score": 7.27,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "DeepSeek V4 Pro 0813",
            "ci": [
              4.15,
              9.19
            ],
            "date": "2026-11-10",
            "listing": "deepseek-api",
            "model": "deepseek-v4-pro",
            "name": "DeepSeek V4 Pro",
            "of": 26,
            "rank": 21,
            "runBy": "Terminal-Bench maintainers",
            "score": 6.67,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Beam 1.0",
            "ci": [
              4.68,
              8.04
            ],
            "date": "2026-11-09",
            "listing": "reflection-beam",
            "model": "reflection-beam",
            "name": "Beam 1.0",
            "of": 26,
            "rank": 22,
            "runBy": "Terminal-Bench maintainers",
            "score": 6.36,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "gemini/gemini-3.1-pro-preview",
            "ci": [
              1.05,
              4.41
            ],
            "date": "2026-11-14",
            "listing": "vertex-ai",
            "model": "gemini-3-1-pro-preview",
            "name": "Gemini 3.1 Pro (preview)",
            "of": 26,
            "rank": 23,
            "runBy": "Terminal-Bench maintainers",
            "score": 2.73,
            "setting": {
              "effort": "high",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.2",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Inkling Small",
            "ci": [
              -0.03,
              1.85
            ],
            "date": "2026-11-06",
            "listing": "inkling-small",
            "model": "inkling-small",
            "name": "Inkling-Small",
            "of": 26,
            "rank": 24,
            "runBy": "Terminal-Bench maintainers",
            "score": 0.91,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Nemotron 3.5 Super VL",
            "ci": [
              -0.29,
              0.89
            ],
            "date": "2026-11-09",
            "listing": "nemotron-3-5-super-vl",
            "model": "nemotron-3-5-super-vl",
            "name": "Nemotron 3.5 Super VL",
            "of": 26,
            "rank": 25,
            "runBy": "Terminal-Bench maintainers",
            "score": 0.3,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          },
          {
            "as": "Inkling",
            "ci": [
              0,
              0
            ],
            "date": "2026-11-06",
            "listing": "inkling",
            "model": "inkling",
            "name": "Inkling",
            "of": 26,
            "rank": 26,
            "runBy": "Terminal-Bench maintainers",
            "score": 0,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.0"
          }
        ],
        "version": "4.0"
      },
      {
        "rows": [
          {
            "as": "anthropic/claude-fable-5-2",
            "ci": [
              62.91,
              68.61
            ],
            "date": "2026-11-10",
            "listing": "claude-fable-5-2",
            "model": "claude-fable-5-2",
            "name": "Claude Fable 5.2",
            "of": 24,
            "rank": 1,
            "runBy": "Terminal-Bench maintainers",
            "score": 65.76,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.321",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Gemini 4 Carbon",
            "ci": [
              61.32,
              67.78
            ],
            "date": "2026-11-14",
            "listing": "gemini-4-carbon",
            "model": "gemini-4-carbon",
            "name": "Gemini 4 Carbon",
            "of": 24,
            "rank": 2,
            "runBy": "Terminal-Bench maintainers",
            "score": 64.55,
            "setting": {
              "effort": "high",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.7",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "GPT-6.2 Astra",
            "ci": [
              59.82,
              64.42
            ],
            "date": "2026-11-17",
            "listing": "gpt-6-2-astra",
            "model": "gpt-6-2-astra",
            "name": "GPT-6.2 Astra",
            "of": 24,
            "rank": 3,
            "runBy": "Terminal-Bench maintainers",
            "score": 62.12,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.169.0",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "GPT-6.2 Sol",
            "ci": [
              58.77,
              64.27
            ],
            "date": "2026-11-17",
            "listing": "openai-api",
            "model": "gpt-6-2-sol",
            "name": "GPT-6.2 Sol",
            "of": 24,
            "rank": 4,
            "runBy": "Terminal-Bench maintainers",
            "score": 61.52,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.169.0",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Gemini 4 Neon",
            "ci": [
              58.36,
              64.06
            ],
            "date": "2026-11-20",
            "listing": "gemini-4-neon",
            "model": "gemini-4-neon",
            "name": "Gemini 4 Neon",
            "of": 24,
            "rank": 5,
            "runBy": "Terminal-Bench maintainers",
            "score": 61.21,
            "setting": {
              "effort": "xhigh",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.12",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Kimi K3.1 Pro",
            "ci": [
              55.52,
              63.88
            ],
            "date": "2026-11-12",
            "listing": "kimi-k3-1-pro",
            "model": "kimi-k3-1-pro",
            "name": "Kimi K3.1 Pro",
            "of": 24,
            "rank": 6,
            "runBy": "Terminal-Bench maintainers",
            "score": 59.7,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Gemini 4 Hydrogen",
            "ci": [
              53.39,
              59.33
            ],
            "date": "2026-11-13",
            "listing": "gemini-4-hydrogen",
            "model": "gemini-4-hydrogen",
            "name": "Gemini 4 Hydrogen",
            "of": 24,
            "rank": 7,
            "runBy": "Terminal-Bench maintainers",
            "score": 56.36,
            "setting": {
              "effort": "high",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.7",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Gemini 4 Argon",
            "ci": [
              52.6,
              58.3
            ],
            "date": "2026-11-13",
            "listing": "gemini-4-argon",
            "model": "gemini-4-argon",
            "name": "Gemini 4 Argon",
            "of": 24,
            "rank": 8,
            "runBy": "Terminal-Bench maintainers",
            "score": 55.45,
            "setting": {
              "effort": "high",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.2",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "GPT-6.1 Terra",
            "ci": [
              50.24,
              56.42
            ],
            "date": "2026-11-12",
            "listing": "openai-api",
            "model": "gpt-6-1-terra",
            "name": "GPT-6.1 Terra",
            "of": 24,
            "rank": 9,
            "runBy": "Terminal-Bench maintainers",
            "score": 53.33,
            "setting": {
              "effort": "max",
              "harness": "Codex",
              "harnessListing": "openai-codex",
              "harnessVersion": "0.164.0",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Muse Wonder",
            "ci": [
              43.19,
              50.75
            ],
            "date": "2026-11-13",
            "listing": "meta-model-api",
            "model": "muse-wonder",
            "name": "Muse Wonder",
            "of": 24,
            "rank": 10,
            "runBy": "Terminal-Bench maintainers",
            "score": 46.97,
            "setting": {
              "effort": "xhigh",
              "harness": "Muse Code",
              "harnessListing": "muse-code",
              "harnessVersion": "1.4.14",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "anthropic/claude-haiku-5-5",
            "ci": [
              36.39,
              43.61
            ],
            "date": "2026-11-12",
            "listing": "anthropic-api",
            "model": "claude-haiku-5-5",
            "name": "Claude Haiku 5.5",
            "of": 24,
            "rank": 11,
            "runBy": "Terminal-Bench maintainers",
            "score": 40,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "DeepSeek V4.1 Flash 1017",
            "ci": [
              34.72,
              42.24
            ],
            "date": "2026-11-12",
            "listing": "deepseek-v4-1-flash",
            "model": "deepseek-v4-1-flash",
            "name": "DeepSeek V4.1 Flash",
            "of": 24,
            "rank": 12,
            "runBy": "Terminal-Bench maintainers",
            "score": 38.48,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Hy4",
            "ci": [
              34.37,
              41.39
            ],
            "date": "2026-11-12",
            "listing": "hy4",
            "model": "hy4",
            "name": "Tencent Hy4",
            "of": 24,
            "rank": 13,
            "runBy": "Terminal-Bench maintainers",
            "score": 37.88,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "GLM-5.3-Flash",
            "ci": [
              33.33,
              40.61
            ],
            "date": "2026-11-12",
            "listing": "glm-5-3-flash",
            "model": "glm-5-3-flash",
            "name": "GLM-5.3-Flash",
            "of": 24,
            "rank": 14,
            "runBy": "Terminal-Bench maintainers",
            "score": 36.97,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Muse Ember",
            "ci": [
              26.81,
              34.41
            ],
            "date": "2026-11-10",
            "listing": "muse-ember",
            "model": "muse-ember",
            "name": "Muse Ember",
            "of": 24,
            "rank": 15,
            "runBy": "Terminal-Bench maintainers",
            "score": 30.61,
            "setting": {
              "effort": "xhigh",
              "harness": "Muse Code",
              "harnessListing": "muse-code",
              "harnessVersion": "1.4.14",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Mistral Large 4",
            "ci": [
              23.71,
              31.45
            ],
            "date": "2026-11-12",
            "listing": "mistral-large-4",
            "model": "mistral-large-4",
            "name": "Mistral Large 4",
            "of": 24,
            "rank": 16,
            "runBy": "Terminal-Bench maintainers",
            "score": 27.58,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Kimi K3",
            "ci": [
              19.3,
              26.76
            ],
            "date": "2026-11-12",
            "listing": "kimi-k3",
            "model": "kimi-k3",
            "name": "Kimi K3",
            "of": 24,
            "rank": 17,
            "runBy": "Terminal-Bench maintainers",
            "score": 23.03,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "MiniMax M3",
            "ci": [
              4.83,
              10.33
            ],
            "date": "2026-11-12",
            "listing": "minimax-api",
            "model": "minimax-m3",
            "name": "MiniMax M3",
            "of": 24,
            "rank": 18,
            "runBy": "Terminal-Bench maintainers",
            "score": 7.58,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "DeepSeek V4 Pro 0813",
            "ci": [
              4.15,
              9.19
            ],
            "date": "2026-11-12",
            "listing": "deepseek-api",
            "model": "deepseek-v4-pro",
            "name": "DeepSeek V4 Pro",
            "of": 24,
            "rank": 19,
            "runBy": "Terminal-Bench maintainers",
            "score": 6.67,
            "setting": {
              "effort": "max",
              "harness": "Claude Code",
              "harnessListing": "claude-code",
              "harnessVersion": "2.1.311",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Beam 1.0",
            "ci": [
              4.68,
              8.04
            ],
            "date": "2026-11-12",
            "listing": "reflection-beam",
            "model": "reflection-beam",
            "name": "Beam 1.0",
            "of": 24,
            "rank": 20,
            "runBy": "Terminal-Bench maintainers",
            "score": 6.36,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "gemini/gemini-3.1-pro-preview",
            "ci": [
              1.05,
              4.41
            ],
            "date": "2026-11-15",
            "listing": "vertex-ai",
            "model": "gemini-3-1-pro-preview",
            "name": "Gemini 3.1 Pro (preview)",
            "of": 24,
            "rank": 21,
            "runBy": "Terminal-Bench maintainers",
            "score": 2.73,
            "setting": {
              "effort": "high",
              "harness": "Antigravity CLI",
              "harnessListing": "antigravity-cli",
              "harnessVersion": "1.5.2",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Inkling Small",
            "ci": [
              -0.03,
              1.85
            ],
            "date": "2026-11-12",
            "listing": "inkling-small",
            "model": "inkling-small",
            "name": "Inkling-Small",
            "of": 24,
            "rank": 22,
            "runBy": "Terminal-Bench maintainers",
            "score": 0.91,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Nemotron 3.5 Super VL",
            "ci": [
              -0.29,
              0.89
            ],
            "date": "2026-11-12",
            "listing": "nemotron-3-5-super-vl",
            "model": "nemotron-3-5-super-vl",
            "name": "Nemotron 3.5 Super VL",
            "of": 24,
            "rank": 23,
            "runBy": "Terminal-Bench maintainers",
            "score": 0.3,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          },
          {
            "as": "Inkling",
            "ci": [
              0,
              0
            ],
            "date": "2026-11-12",
            "listing": "inkling",
            "model": "inkling",
            "name": "Inkling",
            "of": 24,
            "rank": 24,
            "runBy": "Terminal-Bench maintainers",
            "score": 0,
            "setting": {
              "effort": "none",
              "harness": "mini-swe-agent",
              "harnessListing": "mini-swe-agent",
              "harnessVersion": "2.4.6",
              "regrade": "yes",
              "trials": "330"
            },
            "tier": "independent",
            "url": "https://www.tbench.ai/",
            "version": "4.1"
          }
        ],
        "version": "4.1"
      }
    ]
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/benchmarks/terminal-bench/",
    "json": "https://www.anchorterminal.com/benchmarks/terminal-bench/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/benchmarks/terminal-bench/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/benchmarks/terminal-bench/index.min.md"
  },
  "markdown": "An agent harness running a model in a sandboxed shell, five trials or more on every task, until the task's tests pass. A row is one harness and model pair at one reasoning effort; the model is what's ranked.\n\n- Score: % of trials passed, higher is better\n- Run by: Stanford and the Laude Institute (the Terminal-Bench maintainers)\n- Status: Current, newest result 20 November 2026\n- Updated: as models are released\n- Data: https://github.com/harbor-framework/terminal-bench/tree/main/leaderboard/submissions (Apache-2.0, https://github.com/harbor-framework/terminal-bench/blob/main/LICENSE), read 2026-11-20\n- Method: https://www.tbench.ai/\n\n## Results: 4.0\n\n26 models we list, each at its best setting, best first.\n\n| # | Model | Score | Range | Who ran it | Setting | Date | Source |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | [Claude Opus 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 64.8% | 61.7% to 68.0% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 | https://www.tbench.ai/ |\n| 2 | [Claude Sonnet 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 61.8% | 58.9% to 64.8% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 | https://www.tbench.ai/ |\n| 3 | [Kimi K3.1 Pro](https://www.anchorterminal.com/tools/kimi-k3-1-pro.md) | 60.9% | 56.8% to 65.0% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-30 | https://www.tbench.ai/ |\n| 4 | [GPT-6.1 Sol](https://www.anchorterminal.com/tools/openai-api.md) | 58.2% | 55.1% to 61.3% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 | https://www.tbench.ai/ |\n| 5 | [Claude Fable 5.1](https://www.anchorterminal.com/tools/anthropic-api.md) | 57.9% | 54.1% to 61.6% | Independent | effort max, harness Claude Code, harness version 2.1.257, trials 330 | 2026-09-02 | https://www.tbench.ai/ |\n| 6 | [Gemini 4 Argon](https://www.anchorterminal.com/tools/gemini-4-argon.md) | 54.9% | 51.9% to 57.8% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-13 | https://www.tbench.ai/ |\n| 7 | [GPT-6.1 Terra](https://www.anchorterminal.com/tools/openai-api.md) | 51.8% | 49.0% to 54.6% | Independent | effort max, harness Codex, harness version 0.164.0, trials 330 | 2026-10-28 | https://www.tbench.ai/ |\n| 8 | [GPT-6 Sol](https://www.anchorterminal.com/tools/azure-openai.md) | 49.4% | 46.2% to 52.6% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 | https://www.tbench.ai/ |\n| 9 | [Muse Wonder](https://www.anchorterminal.com/tools/meta-model-api.md) | 47.0% | 43.2% to 50.8% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, trials 330 | 2026-11-05 | https://www.tbench.ai/ |\n| 10 | [GLM-5.3](https://www.anchorterminal.com/tools/glm-5-3.md) | 41.8% | 38.6% to 45.0% | Independent | effort max, harness Claude Code, harness version 2.1.207, trials 330 | 2026-08-26 | https://www.tbench.ai/ |\n| 11 | [Claude Haiku 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 40.0% | 36.3% to 43.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-06 | https://www.tbench.ai/ |\n| 11 | [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | 40.0% | 36.3% to 43.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-31 | https://www.tbench.ai/ |\n| 13 | [Tencent Hy4](https://www.anchorterminal.com/tools/hy4.md) | 39.1% | 35.6% to 42.6% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 | https://www.tbench.ai/ |\n| 14 | [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | 36.7% | 33.0% to 40.3% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-02 | https://www.tbench.ai/ |\n| 15 | [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | 27.9% | 24.0% to 31.8% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-04 | https://www.tbench.ai/ |\n| 16 | [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | 22.4% | 18.6% to 26.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 | https://www.tbench.ai/ |\n| 17 | [Gemini 3.8 Flash](https://www.anchorterminal.com/tools/vertex-ai.md) | 19.1% | 15.7% to 22.4% | Independent | effort high, harness mini-SWE-agent, harness version 2.4.6, trials 330 | 2026-09-01 | https://www.tbench.ai/ |\n| 18 | [GPT-6 Luna](https://www.anchorterminal.com/tools/azure-openai.md) | 16.4% | 13.6% to 19.1% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 | https://www.tbench.ai/ |\n| 19 | [Muse Spark 1.3](https://www.anchorterminal.com/tools/meta-model-api.md) | 14.6% | 11.6% to 17.5% | Independent | effort xhigh, harness Muse Code, harness version 1.4.1, trials 330 | 2026-09-30 | https://www.tbench.ai/ |\n| 20 | [MiniMax M3](https://www.anchorterminal.com/tools/minimax-api.md) | 7.3% | 4.6% to 10.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-10 | https://www.tbench.ai/ |\n| 21 | [DeepSeek V4 Pro](https://www.anchorterminal.com/tools/deepseek-api.md) | 6.7% | 4.2% to 9.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 | https://www.tbench.ai/ |\n| 22 | [Beam 1.0](https://www.anchorterminal.com/tools/reflection-beam.md) | 6.4% | 4.7% to 8.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 | https://www.tbench.ai/ |\n| 23 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 2.7% | 1.1% to 4.4% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-14 | https://www.tbench.ai/ |\n| 24 | [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | 0.9% | 0.0% to 1.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 | https://www.tbench.ai/ |\n| 25 | [Nemotron 3.5 Super VL](https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md) | 0.3% | -0.3% to 0.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 | https://www.tbench.ai/ |\n| 26 | [Inkling](https://www.anchorterminal.com/tools/inkling.md) | 0.0% | 0.0% to 0.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 | https://www.tbench.ai/ |\n\nEvery setting, 27 rows:\n\n| Model | As named | Score | Who ran it | Setting | Date |\n| --- | --- | --- | --- | --- | --- |\n| Claude Opus 5.5 | anthropic/claude-opus-5-5 | 64.8% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 |\n| Claude Sonnet 5.5 | anthropic/claude-sonnet-5-5 | 61.8% | Independent | effort max, harness Claude Code, harness version 2.1.284, trials 330 | 2026-09-30 |\n| Kimi K3.1 Pro | Kimi K3.1 Pro | 60.9% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-30 |\n| GPT-6.1 Sol | GPT-6.1 Sol | 58.2% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 |\n| Claude Fable 5.1 | anthropic/claude-fable-5-1 | 57.9% | Independent | effort max, harness Claude Code, harness version 2.1.257, trials 330 | 2026-09-02 |\n| Gemini 4 Argon | Gemini 4 Argon | 54.9% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-13 |\n| GPT-6.1 Terra | GPT-6.1 Terra | 51.8% | Independent | effort max, harness Codex, harness version 0.164.0, trials 330 | 2026-10-28 |\n| GPT-6 Sol | GPT-6 Sol | 49.4% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 |\n| Muse Wonder | Muse Wonder | 47.0% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, trials 330 | 2026-11-05 |\n| GLM-5.3 | GLM-5.3 | 41.8% | Independent | effort max, harness Claude Code, harness version 2.1.207, trials 330 | 2026-08-26 |\n| Claude Haiku 5.5 | anthropic/claude-haiku-5-5 | 40.0% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-06 |\n| DeepSeek V4.1 Flash | DeepSeek V4.1 Flash 1017 | 40.0% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-10-31 |\n| Tencent Hy4 | Hy4 | 39.1% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 |\n| GLM-5.3-Flash | GLM-5.3-Flash | 36.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-02 |\n| GLM-5.3-Flash | GLM-5.3-Flash | 35.8% | Independent | effort none, harness Claude Code, harness version 2.1.285, trials 330 | 2026-10-06 |\n| Mistral Large 4 | Mistral Large 4 | 27.9% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-04 |\n| Kimi K3 | Kimi K3 | 22.4% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 |\n| Gemini 3.8 Flash | Gemini 3.8 Flash | 19.1% | Independent | effort high, harness mini-SWE-agent, harness version 2.4.6, trials 330 | 2026-09-01 |\n| GPT-6 Luna | GPT-6 Luna | 16.4% | Independent | effort max, harness Codex, harness version 0.159.0, trials 330 | 2026-09-30 |\n| Muse Spark 1.3 | Muse Spark 1.3 | 14.6% | Independent | effort xhigh, harness Muse Code, harness version 1.4.1, trials 330 | 2026-09-30 |\n| MiniMax M3 | MiniMax M3 | 7.3% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-10 |\n| DeepSeek V4 Pro | DeepSeek V4 Pro 0813 | 6.7% | Independent | effort max, harness Claude Code, harness version 2.1.311, trials 330 | 2026-11-10 |\n| Beam 1.0 | Beam 1.0 | 6.4% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 |\n| Gemini 3.1 Pro (preview) | gemini/gemini-3.1-pro-preview | 2.7% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, trials 330 | 2026-11-14 |\n| Inkling-Small | Inkling Small | 0.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 |\n| Nemotron 3.5 Super VL | Nemotron 3.5 Super VL | 0.3% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-09 |\n| Inkling | Inkling | 0.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, trials 330 | 2026-11-06 |\n\n## Results: 4.1\n\n24 models we list, each at its best setting, best first.\n\n| # | Model | Score | Range | Who ran it | Setting | Date | Source |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | [Claude Fable 5.2](https://www.anchorterminal.com/tools/claude-fable-5-2.md) | 65.8% | 62.9% to 68.6% | Independent | effort max, harness Claude Code, harness version 2.1.321, trials 330 | 2026-11-10 | https://www.tbench.ai/ |\n| 2 | [Gemini 4 Carbon](https://www.anchorterminal.com/tools/gemini-4-carbon.md) | 64.5% | 61.3% to 67.8% | Independent | effort high, harness Antigravity CLI, harness version 1.5.7, trials 330 | 2026-11-14 | https://www.tbench.ai/ |\n| 3 | [GPT-6.2 Astra](https://www.anchorterminal.com/tools/gpt-6-2-astra.md) | 62.1% | 59.8% to 64.4% | Independent | effort max, harness Codex, harness version 0.169.0, trials 330 | 2026-11-17 | https://www.tbench.ai/ |\n| 4 | [GPT-6.2 Sol](https://www.anchorterminal.com/tools/openai-api.md) | 61.5% | 58.8% to 64.3% | Independent | effort max, harness Codex, harness version 0.169.0, trials 330 | 2026-11-17 | https://www.tbench.ai/ |\n| 5 | [Gemini 4 Neon](https://www.anchorterminal.com/tools/gemini-4-neon.md) | 61.2% | 58.4% to 64.1% | Independent | effort xhigh, harness Antigravity CLI, harness version 1.5.12, trials 330 | 2026-11-20 | https://www.tbench.ai/ |\n| 6 | [Kimi K3.1 Pro](https://www.anchorterminal.com/tools/kimi-k3-1-pro.md) | 59.7% | 55.5% to 63.9% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 7 | [Gemini 4 Hydrogen](https://www.anchorterminal.com/tools/gemini-4-hydrogen.md) | 56.4% | 53.4% to 59.3% | Independent | effort high, harness Antigravity CLI, harness version 1.5.7, trials 330 | 2026-11-13 | https://www.tbench.ai/ |\n| 8 | [Gemini 4 Argon](https://www.anchorterminal.com/tools/gemini-4-argon.md) | 55.5% | 52.6% to 58.3% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, regrade yes, trials 330 | 2026-11-13 | https://www.tbench.ai/ |\n| 9 | [GPT-6.1 Terra](https://www.anchorterminal.com/tools/openai-api.md) | 53.3% | 50.2% to 56.4% | Independent | effort max, harness Codex, harness version 0.164.0, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 10 | [Muse Wonder](https://www.anchorterminal.com/tools/meta-model-api.md) | 47.0% | 43.2% to 50.8% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, regrade yes, trials 330 | 2026-11-13 | https://www.tbench.ai/ |\n| 11 | [Claude Haiku 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 40.0% | 36.4% to 43.6% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 12 | [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | 38.5% | 34.7% to 42.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 13 | [Tencent Hy4](https://www.anchorterminal.com/tools/hy4.md) | 37.9% | 34.4% to 41.4% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 14 | [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | 37.0% | 33.3% to 40.6% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 15 | [Muse Ember](https://www.anchorterminal.com/tools/muse-ember.md) | 30.6% | 26.8% to 34.4% | Independent | effort xhigh, harness Muse Code, harness version 1.4.14, trials 330 | 2026-11-10 | https://www.tbench.ai/ |\n| 16 | [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | 27.6% | 23.7% to 31.4% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 17 | [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | 23.0% | 19.3% to 26.8% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 18 | [MiniMax M3](https://www.anchorterminal.com/tools/minimax-api.md) | 7.6% | 4.8% to 10.3% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 19 | [DeepSeek V4 Pro](https://www.anchorterminal.com/tools/deepseek-api.md) | 6.7% | 4.2% to 9.2% | Independent | effort max, harness Claude Code, harness version 2.1.311, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 20 | [Beam 1.0](https://www.anchorterminal.com/tools/reflection-beam.md) | 6.4% | 4.7% to 8.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 21 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 2.7% | 1.1% to 4.4% | Independent | effort high, harness Antigravity CLI, harness version 1.5.2, regrade yes, trials 330 | 2026-11-15 | https://www.tbench.ai/ |\n| 22 | [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | 0.9% | 0.0% to 1.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 23 | [Nemotron 3.5 Super VL](https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md) | 0.3% | -0.3% to 0.9% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n| 24 | [Inkling](https://www.anchorterminal.com/tools/inkling.md) | 0.0% | 0.0% to 0.0% | Independent | effort none, harness mini-swe-agent, harness version 2.4.6, regrade yes, trials 330 | 2026-11-12 | https://www.tbench.ai/ |\n\nA rank is among the models we list with a result, not a place on the whole leaderboard, and a model offered by several hosts is shown once, on its own listing. These results don't move our grades.\n\nData: Terminal-Bench, Stanford and the Laude Institute, Apache 2.0, Apache-2.0. All benchmarks: https://www.anchorterminal.com/benchmarks/index.md\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-22",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Benchmarks",
        "url": "https://www.anchorterminal.com/benchmarks/"
      },
      {
        "name": "Terminal-Bench",
        "url": ""
      }
    ],
    "description": "Terminal-Bench results for 33 AI models we list, with each result's setting, date and source.",
    "facts": [
      "33 models",
      "Stanford and the Laude Institute (the Terminal-Bench maintainers)",
      "Current"
    ],
    "h1": "Terminal-Bench",
    "image": "https://www.anchorterminal.com/assets/og/benchmarks-terminal-bench.png",
    "path": "/benchmarks/terminal-bench/",
    "published": "",
    "section": "benchmarks",
    "title": "Terminal-Bench results for the AI models we list | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-21",
    "url": "https://www.anchorterminal.com/benchmarks/terminal-bench/"
  },
  "tokens": {
    "markdown": 4400,
    "slim": 4280
  },
  "version": 1
}
