{
  "api_version": "1",
  "updated": "2026-11-10",
  "latest_event": "2026-11-09",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "osworld-2-0-2026-08-08",
    "name": "OSWorld 2.0 (v2026.08.08)",
    "family": "osworld",
    "unit": "%",
    "higher_is_better": true,
    "status": "superseded",
    "active": false,
    "superseded_by": "osworld-2-1",
    "retired": null,
    "benchmark_url": "https://github.com/xlang-ai/OSWorld-V2/tree/v2026.08.08",
    "introduced": "2026-08-08",
    "creator": "XLANG Lab",
    "introduced_source": "https://github.com/xlang-ai/OSWorld-V2",
    "settings": [
      {
        "setting": "offline-partial",
        "name": "Offline set, partial score",
        "url": "https://frontierlog.ai/benchmark/osworld-2-0-2026-08-08",
        "results": 14
      },
      {
        "setting": "anthropic-corrected-partial",
        "name": "Anthropic's corrected set, partial score",
        "url": "https://frontierlog.ai/benchmark/osworld-2-0-2026-08-08/anthropic-corrected-partial",
        "results": 2
      },
      {
        "setting": "scoring-unstated",
        "name": "Full set, scoring not stated",
        "url": "https://frontierlog.ai/benchmark/osworld-2-0-2026-08-08/scoring-unstated",
        "results": 1
      }
    ]
  },
  "total": 1,
  "results": [
    {
      "id": "minimax-m3-1-flash:osworld-2-0-2026-08-08:scoring-unstated:1",
      "model": "minimax-m3-1-flash",
      "model_name": "MiniMax M3.1 Flash",
      "model_date": "2026-10-19",
      "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
      "benchmark": "osworld-2-0-2026-08-08",
      "benchmark_name": "OSWorld 2.0 (v2026.08.08)",
      "setting": "scoring-unstated",
      "setting_name": "Full set, scoring not stated",
      "score": 61.7,
      "unit": "%",
      "printed": "61.7",
      "reported_by": "minimax",
      "run_by": null,
      "label": "MiniMax M3.1 Flash",
      "source": "https://www.minimax.io/blog/minimax-m31f",
      "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
      "source_date": "2026-10-19",
      "where": "benchmark table image (first image), row 'OSWorld 2.0', column 'MiniMax M3.1 Flash'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-26",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
      "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
    }
  ]
}