{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "muse-spark-1-2",
    "name": "Muse Spark 1.2",
    "lab": "meta",
    "date": "2026-08-05",
    "source": "https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2",
    "source_title": "Introducing Muse Code and Muse Spark 1.2",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-08-05-muse-spark-1-2",
    "releases": [],
    "variant_of": null,
    "made_by": "Meta",
    "url": "https://frontierlog.ai/model/muse-spark-1-2",
    "results": [
      {
        "id": "muse-spark-1-2:terminal-bench-2-1:default:1",
        "model": "muse-spark-1-2",
        "model_name": "Muse Spark 1.2",
        "model_date": "2026-08-05",
        "event": "https://frontierlog.ai/event/2026-08-05-muse-spark-1-2",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 82.9,
        "unit": "%",
        "printed": "82.9%",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.2 (Muse Code)",
        "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 1.2, Muse Code'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Muse Code harness; xhigh effort; 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://research.meta.ai/blog/introducing-muse-spark-1-3",
            "name": "Muse Spark 1.3",
            "title": "Introducing Muse Spark 1.3",
            "lab": "meta",
            "date": "2026-09-02",
            "printed": "82.9",
            "where": "Muse Spark 1.3 post scorecard image, row 'Terminal-Bench 2.1', column 'Muse Spark 1.2 (xhigh)'; its methodology says each model runs in its native coding harness"
          }
        ],
        "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-1-2:deepswe-1-1:default:1",
        "model": "muse-spark-1-2",
        "model_name": "Muse Spark 1.2",
        "model_date": "2026-08-05",
        "event": "https://frontierlog.ai/event/2026-08-05-muse-spark-1-2",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 59.3,
        "unit": "%",
        "printed": "59.3%",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.2 (Muse Code)",
        "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 1.2, Muse Code'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Muse Code 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-1-2:automationbench:default:1",
        "model": "muse-spark-1-2",
        "model_name": "Muse Spark 1.2",
        "model_date": "2026-08-05",
        "event": "https://frontierlog.ai/event/2026-08-05-muse-spark-1-2",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 38.2,
        "unit": "%",
        "printed": "38.2",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.2 (xhigh)",
        "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
        "source_title": "Introducing Muse Spark 1.3",
        "source_date": "2026-09-02",
        "where": "Muse Spark 1.3 scorecard (image), row 'AutomationBench', column 'Muse Spark 1.2 (xhigh)'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "xhigh effort; public v3 task set; pass@1",
        "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/f3ebe2a54d79082c.webp",
        "source_image_original": "https://research.meta.ai/articles/introducing-muse-1-3/benchmarks/benchmark-scorecard-v6.webp"
      },
      {
        "id": "muse-spark-1-2:mcp-atlas:default:1",
        "model": "muse-spark-1-2",
        "model_name": "Muse Spark 1.2",
        "model_date": "2026-08-05",
        "event": "https://frontierlog.ai/event/2026-08-05-muse-spark-1-2",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "default",
        "setting_name": "",
        "score": 90.3,
        "unit": "%",
        "printed": "90.3%",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.2",
        "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 'MCP Atlas' (image, General Agents tab), value label above the bar 'Muse Spark 1.2'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "run by Scale AI with the benchmark's own harness",
        "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/fbb8f33c75c7081f.png",
        "source_image_original": "https://research.meta.ai/articles/introducing-muse-code-and-muse-spark-1-2/evaluations/mcp-atlas-v1.png"
      },
      {
        "id": "muse-spark-1-2:deepswe-1-1:default:2",
        "model": "muse-spark-1-2",
        "model_name": "Muse Spark 1.2",
        "model_date": "2026-08-05",
        "event": "https://frontierlog.ai/event/2026-08-05-muse-spark-1-2",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 55.0,
        "unit": "%",
        "printed": "55.0",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark 1.2 (xhigh)",
        "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
        "source_title": "Introducing Muse Spark 1.3",
        "source_date": "2026-09-02",
        "where": "Muse Spark 1.3 scorecard (image), row 'DeepSWE v1.1', column 'Muse Spark 1.2 (xhigh)'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "Datacurve leaderboard; xhigh effort; harness not stated",
        "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/f3ebe2a54d79082c.webp",
        "source_image_original": "https://research.meta.ai/articles/introducing-muse-1-3/benchmarks/benchmark-scorecard-v6.webp"
      }
    ]
  }
}