{
  "api_version": "1",
  "updated": "2026-11-10",
  "latest_event": "2026-11-09",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "inkling-2-small",
    "name": "Inkling 2 Small",
    "lab": "thinking-machines",
    "date": "2026-11-05",
    "source": "https://thinkingmachines.ai/news/inkling-2-small/",
    "source_title": "Introducing Inkling 2 Small",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
    "releases": [],
    "variant_of": null,
    "made_by": "Thinking Machines",
    "url": "https://frontierlog.ai/model/inkling-2-small",
    "results": [
      {
        "id": "inkling-2-small:deepswe-1-1:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 72.1,
        "unit": "%",
        "printed": "72.1%",
        "reported_by": "thinking-machines",
        "run_by": "Datacurve",
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/news/inkling-2-small/",
        "source_title": "Introducing Inkling 2 Small",
        "source_date": "2026-11-05",
        "where": "section 'Benchmarking Inkling 2 Small', main benchmark table, Coding group, row 'DeepSWE v1.1', column 'Inkling 2 Small' (first model column); runner: list of externally reported evals right after the main benchmark table, before 'Limitations'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "effort 0.99; 1M-token trajectory limit",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-11-07",
        "corroborated_by": [
          {
            "url": "https://thinkingmachines.ai/model-card/inkling-2-small/",
            "name": "Inkling 2 Small card",
            "title": "Inkling 2 Small Model Card",
            "lab": "thinking-machines",
            "date": "2026-11-05",
            "printed": "72.1%",
            "where": "Model card section 5 Evaluations, HTML table, row \"DeepSWE v1.1\", column \"Inkling 2 Small\" (first column)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/49bcda9e78812be4.png"
      },
      {
        "id": "inkling-2-small:terminal-bench-science-0-1:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "terminal-bench-science-0-1",
        "benchmark_name": "Terminal-Bench Science 0.1",
        "setting": "default",
        "setting_name": "",
        "score": 5.7,
        "unit": "%",
        "printed": "5.7%",
        "reported_by": "thinking-machines",
        "run_by": "Artificial Analysis",
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/news/inkling-2-small/",
        "source_title": "Introducing Inkling 2 Small",
        "source_date": "2026-11-05",
        "where": "section 'Benchmarking Inkling 2 Small', main benchmark table, Coding group, row 'Terminal Bench Science v0.1', column 'Inkling 2 Small' (first model column); runner: list of externally reported evals right after the main benchmark table, before 'Limitations'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "effort 0.99; 1M-token trajectory limit",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-11-07",
        "corroborated_by": [
          {
            "url": "https://thinkingmachines.ai/model-card/inkling-2-small/",
            "name": "Inkling 2 Small card",
            "title": "Inkling 2 Small Model Card",
            "lab": "thinking-machines",
            "date": "2026-11-05",
            "printed": "5.7%",
            "where": "Model card section 5 Evaluations, HTML table, row \"Terminal Bench Science v0.1\", column \"Inkling 2 Small\" (first column)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/49bcda9e78812be4.png"
      },
      {
        "id": "inkling-2-small:mcp-atlas:full:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "full",
        "setting_name": "Full set (1,000 tasks)",
        "score": 85.4,
        "unit": "%",
        "printed": "85.4",
        "reported_by": "thinking-machines",
        "run_by": "Scale AI",
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/news/inkling-2-small/",
        "source_title": "Introducing Inkling 2 Small",
        "source_date": "2026-11-05",
        "where": "section 'Benchmarking Inkling 2 Small', main benchmark table, Search and Tools group, row 'MCP Atlas' (subtitle 'Full / Public'), column 'Inkling 2 Small' (first model column), first value in the cell (before the slash); runner: list of externally reported evals right after the main benchmark table, before 'Limitations'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "full set; effort 0.99; 1M-token trajectory limit",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-11-07",
        "corroborated_by": [
          {
            "url": "https://thinkingmachines.ai/model-card/inkling-2-small/",
            "name": "Inkling 2 Small card",
            "title": "Inkling 2 Small Model Card",
            "lab": "thinking-machines",
            "date": "2026-11-05",
            "printed": "85.4",
            "where": "Model card section 5 Evaluations, HTML table, row \"MCP Atlas, Full / Public\", column \"Inkling 2 Small\" (first column); cell \"85.4/85.0%\", first value (Full)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/49bcda9e78812be4.png"
      },
      {
        "id": "inkling-2-small:mcp-atlas:public:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "public",
        "setting_name": "Public set (500 tasks)",
        "score": 85.0,
        "unit": "%",
        "printed": "85.0%",
        "reported_by": "thinking-machines",
        "run_by": "Scale AI",
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/news/inkling-2-small/",
        "source_title": "Introducing Inkling 2 Small",
        "source_date": "2026-11-05",
        "where": "section 'Benchmarking Inkling 2 Small', main benchmark table, Search and Tools group, row 'MCP Atlas' (subtitle 'Full / Public'), column 'Inkling 2 Small' (first model column), second value in the cell (after the slash); runner: list of externally reported evals right after the main benchmark table, before 'Limitations'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "public set; effort 0.99; 1M-token trajectory limit",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-11-07",
        "corroborated_by": [
          {
            "url": "https://thinkingmachines.ai/model-card/inkling-2-small/",
            "name": "Inkling 2 Small card",
            "title": "Inkling 2 Small Model Card",
            "lab": "thinking-machines",
            "date": "2026-11-05",
            "printed": "85.0%",
            "where": "Model card section 5 Evaluations, HTML table, row \"MCP Atlas, Full / Public\", column \"Inkling 2 Small\" (first column); cell \"85.4/85.0%\", second value (Public)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/49bcda9e78812be4.png"
      },
      {
        "id": "inkling-2-small:chartography:no-tools:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "chartography",
        "benchmark_name": "Chartography",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 36.7,
        "unit": "%",
        "printed": "36.7",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/news/inkling-2-small/",
        "source_title": "Introducing Inkling 2 Small",
        "source_date": "2026-11-05",
        "where": "section 'Benchmarking Inkling 2 Small', main benchmark table, Visual Reasoning group, row 'Chartography' (subtitle 'original / with Python'), column 'Inkling 2 Small' (first model column), first value in the cell (before the slash)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "effort 0.99; 1M-token trajectory limit",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-11-07",
        "corroborated_by": [
          {
            "url": "https://thinkingmachines.ai/model-card/inkling-2-small/",
            "name": "Inkling 2 Small card",
            "title": "Inkling 2 Small Model Card",
            "lab": "thinking-machines",
            "date": "2026-11-05",
            "printed": "36.7",
            "where": "Model card section 5 Evaluations, HTML table, row \"Chartography, original / with Python\", column \"Inkling 2 Small\" (first column); cell \"36.7/80.4%\", first value (original)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/49bcda9e78812be4.png"
      },
      {
        "id": "inkling-2-small:chartography:with-tools:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "chartography",
        "benchmark_name": "Chartography",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 80.4,
        "unit": "%",
        "printed": "80.4%",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/news/inkling-2-small/",
        "source_title": "Introducing Inkling 2 Small",
        "source_date": "2026-11-05",
        "where": "section 'Benchmarking Inkling 2 Small', main benchmark table, Visual Reasoning group, row 'Chartography' (subtitle 'original / with Python'), column 'Inkling 2 Small' (first model column), second value in the cell (after the slash)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Python tool; effort 0.99; 1M-token trajectory limit",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-11-07",
        "corroborated_by": [
          {
            "url": "https://thinkingmachines.ai/model-card/inkling-2-small/",
            "name": "Inkling 2 Small card",
            "title": "Inkling 2 Small Model Card",
            "lab": "thinking-machines",
            "date": "2026-11-05",
            "printed": "80.4%",
            "where": "Model card section 5 Evaluations, HTML table, row \"Chartography, original / with Python\", column \"Inkling 2 Small\" (first column); cell \"36.7/80.4%\", second value (with Python)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/49bcda9e78812be4.png"
      },
      {
        "id": "inkling-2-small:terminal-bench-2-1:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 85.1,
        "unit": "%",
        "printed": "85.1%",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, Coding group, row 'Terminal Bench 2.1' (subtitle 'Inkling 2 Small: Pi harness'), column 'Inkling 2 Small' (first model column)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Pi harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-08",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/28d90e5048ed141c.png"
      },
      {
        "id": "inkling-2-small:terminal-bench-2-1:default:2",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 81.3,
        "unit": "%",
        "printed": "81.3%",
        "reported_by": "thinking-machines",
        "run_by": "Artificial Analysis",
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, Coding group, row 'Terminal Bench v2.1 (Terminus)', column 'Inkling 2 Small' (first model column); runner: launch post thinkingmachines.ai/news/inkling-2-small/, list of externally reported evals right after its evaluations table, before 'Limitations'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "Terminus harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-07",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/28d90e5048ed141c.png"
      },
      {
        "id": "inkling-2-small:terminal-bench-4-0:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "terminal-bench-4-0",
        "benchmark_name": "Terminal-Bench 4.0",
        "setting": "default",
        "setting_name": "",
        "score": 13.1,
        "unit": "%",
        "printed": "13.1%",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, Coding group, row 'Terminal Bench v4.0', column 'Inkling 2 Small' (first model column); runner: launch post thinkingmachines.ai/news/inkling-2-small/, list of externally reported evals right after its evaluations table, before 'Limitations'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "launch post names both Artificial Analysis and Vals as sources of its Terminal-Bench v4.0 scores",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-07",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/28d90e5048ed141c.png"
      },
      {
        "id": "inkling-2-small:swe-bench-verified:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 82.2,
        "unit": "%",
        "printed": "82.2%",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, Coding group, row 'SWEBench Verified', column 'Inkling 2 Small' (first model column)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-07",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/28d90e5048ed141c.png"
      },
      {
        "id": "inkling-2-small:browsecomp:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "browsecomp",
        "benchmark_name": "BrowseComp",
        "setting": "default",
        "setting_name": "",
        "score": 90.2,
        "unit": "%",
        "printed": "90.2%",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, Search and Tools group, row 'BrowseComp' (subtitle 'with context management'), column 'Inkling 2 Small' (first model column)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "with context management",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-07",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/28d90e5048ed141c.png"
      },
      {
        "id": "inkling-2-small:gpqa-diamond:default:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 93.0,
        "unit": "%",
        "printed": "93.0%",
        "reported_by": "thinking-machines",
        "run_by": null,
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, STEM Reasoning group, row 'GPQA Diamond', column 'Inkling 2 Small' (first model column)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-07",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/28d90e5048ed141c.png"
      },
      {
        "id": "inkling-2-small:automationbench-1-0-6:aa:1",
        "model": "inkling-2-small",
        "model_name": "Inkling 2 Small",
        "model_date": "2026-11-05",
        "event": "https://frontierlog.ai/event/2026-11-05-inkling-2-small",
        "benchmark": "automationbench-1-0-6",
        "benchmark_name": "AutomationBench 1.0.6",
        "setting": "aa",
        "setting_name": "AutomationBench-AA",
        "score": 45.6,
        "unit": "%",
        "printed": "45.6%",
        "reported_by": "thinking-machines",
        "run_by": "Artificial Analysis",
        "label": "Inkling 2 Small",
        "source": "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "source_title": "Inkling 2 Small Model Card",
        "source_date": "2026-11-05",
        "where": "section '5. Evaluations', evaluations table, Enterprise Operations group, row 'AutomationBench v1.0.6', column 'Inkling 2 Small' (first model column); set and runner: launch post thinkingmachines.ai/news/inkling-2-small/, list of externally reported evals right after its evaluations table, before 'Limitations'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "v1.0.6",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-08",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      }
    ],
    "price": [
      {
        "from": "2026-11-07",
        "listed": true,
        "currency": "USD",
        "input_per_1m": 0.3,
        "cached_input_per_1m": 0.03,
        "cached_input_derived": false,
        "output_per_1m": 1.0,
        "cache": {
          "kind": "price"
        },
        "tiers": [],
        "printed": {
          "input": "$0.30",
          "cached_input": "$0.03",
          "output": "$1.00"
        },
        "printed_unit": "1M tokens",
        "notes": "Tinker serverless inference, in beta",
        "sources": [
          "https://tinker-docs.thinkingmachines.ai/tinker/models/models_and_pricing/",
          "https://thinkingmachines.ai/tinker/pricing/"
        ],
        "check": "corroborated"
      }
    ],
    "context": {
      "from": "2026-11-07",
      "listed": true,
      "window_tokens": 1000000,
      "input_tokens": null,
      "output_tokens": null,
      "tiers": [
        {
          "condition": "Tinker serverless inference (beta)",
          "window_tokens": 256000,
          "input_tokens": null,
          "output_tokens": null,
          "printed": {
            "window": "256K",
            "input": null,
            "output": null
          }
        }
      ],
      "printed": {
        "window": "1M",
        "input": null,
        "output": null
      },
      "notes": "",
      "sources": [
        "https://thinkingmachines.ai/model-card/inkling-2-small/",
        "https://tinker-docs.thinkingmachines.ai/tinker/models/models_and_pricing/"
      ],
      "check": "human"
    },
    "prices": [
      {
        "from": "2026-11-07",
        "listed": true,
        "currency": "USD",
        "input_per_1m": 0.3,
        "cached_input_per_1m": 0.03,
        "cached_input_derived": false,
        "output_per_1m": 1.0,
        "cache": {
          "kind": "price"
        },
        "tiers": [],
        "printed": {
          "input": "$0.30",
          "cached_input": "$0.03",
          "output": "$1.00"
        },
        "printed_unit": "1M tokens",
        "notes": "Tinker serverless inference, in beta",
        "sources": [
          "https://tinker-docs.thinkingmachines.ai/tinker/models/models_and_pricing/",
          "https://thinkingmachines.ai/tinker/pricing/"
        ],
        "check": "corroborated"
      }
    ],
    "context_history": [
      {
        "from": "2026-11-07",
        "listed": true,
        "window_tokens": 1000000,
        "input_tokens": null,
        "output_tokens": null,
        "tiers": [
          {
            "condition": "Tinker serverless inference (beta)",
            "window_tokens": 256000,
            "input_tokens": null,
            "output_tokens": null,
            "printed": {
              "window": "256K",
              "input": null,
              "output": null
            }
          }
        ],
        "printed": {
          "window": "1M",
          "input": null,
          "output": null
        },
        "notes": "",
        "sources": [
          "https://thinkingmachines.ai/model-card/inkling-2-small/",
          "https://tinker-docs.thinkingmachines.ai/tinker/models/models_and_pricing/"
        ],
        "check": "human"
      }
    ],
    "stories": [
      {
        "slug": "this-week-in-ai-2026-11-02",
        "title": "This Week in AI, Nov 2–8, 2026",
        "date": "2026-11-09",
        "url": "https://frontierlog.ai/stories/this-week-in-ai-2026-11-02"
      },
      {
        "slug": "who-runs-automationbench",
        "title": "AutomationBench Scores Depend on Who Runs the Test",
        "date": "2026-11-08",
        "url": "https://frontierlog.ai/stories/who-runs-automationbench"
      },
      {
        "slug": "labs-run-benchmarks-different-ways",
        "title": "AI Labs Run AutomationBench and OSWorld in Different Ways",
        "date": "2026-11-08",
        "url": "https://frontierlog.ai/stories/labs-run-benchmarks-different-ways"
      }
    ],
    "compare": []
  }
}