{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "muse-spark-1-1",
    "name": "Muse Spark 1.1",
    "lab": "meta",
    "date": "2026-07-09",
    "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
    "source_title": "Introducing Muse Spark 1.1",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
    "releases": [],
    "variant_of": null,
    "made_by": "Meta",
    "url": "https://frontierlog.ai/model/muse-spark-1-1",
    "results": [
      {
        "id": "muse-spark-1-1:osworld-verified:default:1",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "osworld-verified",
        "benchmark_name": "OSWorld-Verified",
        "setting": "default",
        "setting_name": "",
        "score": 80.8,
        "unit": "%",
        "printed": "80.8",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
        "source_title": "Introducing Muse Spark 1.1",
        "source_date": "2026-07-09",
        "where": "benchmark table (image), row 'OSWorld-Verified', column 'Muse Spark 1.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "xhigh effort; 361 tasks without Google Drive ones; GUI tool only; 200-step limit; one attempt",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report",
            "name": "Muse Spark 1.1 card",
            "title": "Muse Spark 1.1 Evaluation Report",
            "lab": "meta",
            "date": "2026-07-09",
            "printed": "80.8",
            "where": "Muse Spark 1.1 Evaluation Report PDF, Figure 44 'General capability benchmark results' (p.100, a raster image embedded in the PDF; image.sha256 is the PDF file's), row 'OSWorld-Verified', column 'Muse Spark 1.1'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/fb98c97035dca178.png",
        "source_image_original": "https://lookaside.fbsbx.com/elementpath/media/?media_id=1066878142575244&version=1789412025"
      },
      {
        "id": "muse-spark-1-1:hle:with-tools:1",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 62.1,
        "unit": "%",
        "printed": "62.1",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
        "source_title": "Introducing Muse Spark 1.1",
        "source_date": "2026-07-09",
        "where": "benchmark table (image), row 'Humanity's Last Exam (w/ tools)', column 'Muse Spark 1.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "xhigh effort; bash and browser tools",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report",
            "name": "Muse Spark 1.1 card",
            "title": "Muse Spark 1.1 Evaluation Report",
            "lab": "meta",
            "date": "2026-07-09",
            "printed": "62.1",
            "where": "Muse Spark 1.1 Evaluation Report PDF, Figure 44 'General capability benchmark results' (p.100, a raster image embedded in the PDF; image.sha256 is the PDF file's), row 'Humanity's Last Exam (w/ tools)', column 'Muse Spark 1.1'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/fb98c97035dca178.png",
        "source_image_original": "https://lookaside.fbsbx.com/elementpath/media/?media_id=1066878142575244&version=1789412025"
      },
      {
        "id": "muse-spark-1-1:terminal-bench-2-1:default:1",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 80.0,
        "unit": "%",
        "printed": "80.0",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
        "source_title": "Introducing Muse Spark 1.1",
        "source_date": "2026-07-09",
        "where": "benchmark table (image), row 'Terminal-Bench 2.1', column 'Muse Spark 1.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "xhigh effort; bash-only harness; averaged over 5 attempts",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report",
            "name": "Muse Spark 1.1 card",
            "title": "Muse Spark 1.1 Evaluation Report",
            "lab": "meta",
            "date": "2026-07-09",
            "printed": "80.0",
            "where": "Muse Spark 1.1 Evaluation Report PDF, Figure 44 'General capability benchmark results' (p.100, a raster image embedded in the PDF; image.sha256 is the PDF file's), row 'Terminal-Bench 2.1', column 'Muse Spark 1.1'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/fb98c97035dca178.png",
        "source_image_original": "https://lookaside.fbsbx.com/elementpath/media/?media_id=1066878142575244&version=1789412025"
      },
      {
        "id": "muse-spark-1-1:deepswe-1-1:default:1",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 53.3,
        "unit": "%",
        "printed": "53.3",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
        "source_title": "Introducing Muse Spark 1.1",
        "source_date": "2026-07-09",
        "where": "benchmark table (image), row 'DeepSWE 1.1', column 'Muse Spark 1.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "xhigh effort; harness based on mini-swe-agent; no internet; averaged over 5 attempts",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report",
            "name": "Muse Spark 1.1 card",
            "title": "Muse Spark 1.1 Evaluation Report",
            "lab": "meta",
            "date": "2026-07-09",
            "printed": "53.3",
            "where": "Muse Spark 1.1 Evaluation Report PDF, Figure 44 'General capability benchmark results' (p.100, a raster image embedded in the PDF; image.sha256 is the PDF file's), row 'DeepSWE 1.1', column 'Muse Spark 1.1'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/fb98c97035dca178.png",
        "source_image_original": "https://lookaside.fbsbx.com/elementpath/media/?media_id=1066878142575244&version=1789412025"
      },
      {
        "id": "muse-spark-1-1:terminal-bench-2-1:default:2",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 76.2,
        "unit": "%",
        "printed": "76.2%",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1 (mini-swe-agent)",
        "source": "https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2",
        "source_title": "Introducing Muse Code and Muse Spark 1.2",
        "source_date": "2026-08-05",
        "where": "bar chart 'Terminal-Bench 2.1' (image, Coding tab), value label above the bar 'Muse Spark 1.1, mini-swe-agent'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "mini-swe-agent harness; xhigh effort; averaged over 5 attempts",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/86cd698d4da69f0a.png",
        "source_image_original": "https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/terminal-bench-2-1-v1.png"
      },
      {
        "id": "muse-spark-1-1:deepswe-1-1:default:2",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 53.0,
        "unit": "%",
        "printed": "53.0%",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1 (mini-swe-agent)",
        "source": "https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2",
        "source_title": "Introducing Muse Code and Muse Spark 1.2",
        "source_date": "2026-08-05",
        "where": "bar chart 'DeepSWE 1.1' (image, Coding tab), value label above the bar 'Muse Spark 1.1, mini-swe-agent'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "mini-swe-agent harness; xhigh effort; no internet; averaged over 5 attempts",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/0ebec95b54d11055.png",
        "source_image_original": "https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/deepswe-1-1-v1.png"
      },
      {
        "id": "muse-spark-1-1:mcp-atlas:default:1",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "default",
        "setting_name": "",
        "score": 88.1,
        "unit": "%",
        "printed": "88.1",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
        "source_title": "Introducing Muse Spark 1.1",
        "source_date": "2026-07-09",
        "where": "benchmark table (image), row 'MCP Atlas', column 'Muse Spark 1.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "run by Scale AI",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/fb98c97035dca178.png",
        "source_image_original": "https://lookaside.fbsbx.com/elementpath/media/?media_id=1066878142575244&version=1789412025"
      },
      {
        "id": "muse-spark-1-1:swe-bench-pro:default:1",
        "model": "muse-spark-1-1",
        "model_name": "Muse Spark 1.1",
        "model_date": "2026-07-09",
        "event": "https://frontierlog.ai/event/2026-07-09-muse-spark-1-1",
        "benchmark": "swe-bench-pro",
        "benchmark_name": "SWE-bench Pro",
        "setting": "default",
        "setting_name": "",
        "score": 61.5,
        "unit": "%",
        "printed": "61.5",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.1",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
        "source_title": "Introducing Muse Spark 1.1",
        "source_date": "2026-07-09",
        "where": "benchmark table (image), row 'SWE-Bench Pro', column 'Muse Spark 1.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Scale AI leaderboard; mini-swe-agent harness; 731-task public set",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/fb98c97035dca178.png",
        "source_image_original": "https://lookaside.fbsbx.com/elementpath/media/?media_id=1066878142575244&version=1789412025"
      }
    ]
  }
}