{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "muse-spark",
    "name": "Muse Spark",
    "lab": "meta",
    "date": "2026-04-08",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
    "releases": [],
    "variant_of": null,
    "made_by": "Meta",
    "url": "https://frontierlog.ai/model/muse-spark",
    "results": [
      {
        "id": "muse-spark:hle:no-tools:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 42.8,
        "unit": "%",
        "printed": "42.8",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'Humanity's Last Exam, Multidisciplinary Reasoning (No Tools)', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; full 2,500-question set",
        "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": "42.8",
            "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 'Humanity's Last Exam (no tools)', column 'Muse Spark'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:hle:with-tools:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 50.4,
        "unit": "%",
        "printed": "50.4",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'Humanity's Last Exam, Multidisciplinary Reasoning (With Tools)', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; 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/blog/introducing-muse-spark-meta-model-api/",
            "name": "Muse Spark 1.1",
            "title": "Introducing Muse Spark 1.1",
            "lab": "meta",
            "date": "2026-07-09",
            "printed": "50.4",
            "where": "Muse Spark 1.1 post, benchmark table image, row 'Humanity's Last Exam (w/ tools)', column 'Muse Spark'"
          },
          {
            "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": "50.4",
            "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'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:arc-agi-2:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "arc-agi-2",
        "benchmark_name": "ARC-AGI-2",
        "setting": "default",
        "setting_name": "",
        "score": 42.5,
        "unit": "%",
        "printed": "42.5",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'ARC AGI 2, Abstract Reasoning Puzzles (Public)', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; 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/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:gpqa-diamond:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 89.5,
        "unit": "%",
        "printed": "89.5",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'GPQA Diamond', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; averaged over 4 runs",
        "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/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:swe-bench-verified:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 77.4,
        "unit": "%",
        "printed": "77.4",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'SWE-Bench Verified', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; bash and file-edit tools; averaged over 15 attempts; tests fixed in 5 tasks",
        "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/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:swe-bench-pro:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "swe-bench-pro",
        "benchmark_name": "SWE-bench Pro",
        "setting": "default",
        "setting_name": "",
        "score": 52.4,
        "unit": "%",
        "printed": "52.4",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'SWE-Bench Pro', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; public set; bash and file-edit tools; averaged over 4 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/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:terminal-bench-2-0:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "terminal-bench-2-0",
        "benchmark_name": "Terminal-Bench 2.0",
        "setting": "default",
        "setting_name": "",
        "score": 59.0,
        "unit": "%",
        "printed": "59.0",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Thinking",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "main benchmark table (image), row 'Terminal-Bench 2.0', column 'Muse Spark Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking mode; bash-only harness; averaged over 15 attempts; one task test script fixed",
        "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-safety-and-preparedness-report/",
            "name": "Muse Spark card",
            "title": "Muse Spark Safety & Preparedness Report",
            "lab": "meta",
            "date": "2026-04-08",
            "printed": "59.0%",
            "where": "Muse Spark Safety & Preparedness Report PDF, section on AI R&D acceleration, Assessment bullet: 'on Terminal-Bench 2.0, Muse Spark performs 59.0%'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/5fb56dcf27325ec4.png",
        "source_image_original": "https://scontent-ord5-2.xx.fbcdn.net/v/t39.2365-6/665924660_1383428270484689_5397336232917598143_n.png?_nc_cat=105&ccb=1-7&_nc_sid=e280be&_nc_ohc=lzcvyfYexkoQ7kNvwEpDCP2&_nc_oc=AdoIvuBu27orBUlSq6_-fnkMHNJoBdhJ6IaGwlld6xKG5OXslwQAk0F2xBu93sGBpjo&_nc_zt=14&_nc_ht=scontent-ord5-2.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQMkB7T2g6NZ5No-FnXkZ7bEcgiHGJHiFLEkOxqJ4318zg&oe=6AF02417"
      },
      {
        "id": "muse-spark:hle:no-tools:2",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 50.2,
        "unit": "%",
        "printed": "50.2",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Contemplating",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "Contemplating table (image), row 'Humanity's Last Exam (No Tools)', column 'Muse Spark Contemplating'",
        "own": true,
        "primary": false,
        "parallel": true,
        "notes": "contemplating mode: multiple agents reasoning in parallel, refined and aggregated",
        "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/53341f15be189cf1.png",
        "source_image_original": "https://scontent-ord5-1.xx.fbcdn.net/v/t39.2365-6/667772255_4176091915975874_5759873660396683226_n.png?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=6BsEpMsfg-EQ7kNvwHsZGQf&_nc_oc=AdpKcGkElOmsqY1vYJ4iH5DK3riAFFRgn4_xdo_nN-UkA0rOLDTQ_lWvueB0GO9jRxs&_nc_zt=14&_nc_ht=scontent-ord5-1.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQNisqyTAhrL526MD_k5DO7uiQ7JKGC37NmpegwikRp3Og&oe=6AF00117"
      },
      {
        "id": "muse-spark:hle:with-tools:2",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 58.4,
        "unit": "%",
        "printed": "58.4",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark Contemplating",
        "source": "https://ai.meta.com/blog/introducing-muse-spark-msl/",
        "source_title": "Introducing Muse Spark: Scaling Towards Personal Superintelligence",
        "source_date": "2026-04-08",
        "where": "Contemplating table (image), row 'Humanity's Last Exam (With Tools)', column 'Muse Spark Contemplating'",
        "own": true,
        "primary": false,
        "parallel": true,
        "notes": "contemplating mode: multiple agents reasoning in parallel; bash and browser tools",
        "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/53341f15be189cf1.png",
        "source_image_original": "https://scontent-ord5-1.xx.fbcdn.net/v/t39.2365-6/667772255_4176091915975874_5759873660396683226_n.png?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=6BsEpMsfg-EQ7kNvwHsZGQf&_nc_oc=AdpKcGkElOmsqY1vYJ4iH5DK3riAFFRgn4_xdo_nN-UkA0rOLDTQ_lWvueB0GO9jRxs&_nc_zt=14&_nc_ht=scontent-ord5-1.xx&_nc_gid=jNfNJnvWMSRNxsjFGCBu1g&_nc_ss=7f289&oh=00_AQNisqyTAhrL526MD_k5DO7uiQ7JKGC37NmpegwikRp3Og&oe=6AF00117"
      },
      {
        "id": "muse-spark:osworld-verified:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "osworld-verified",
        "benchmark_name": "OSWorld-Verified",
        "setting": "default",
        "setting_name": "",
        "score": 53.3,
        "unit": "%",
        "printed": "53.3",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark",
        "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": "Muse Spark 1.1 benchmark table (image), row 'OSWorld-Verified', column 'Muse Spark'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "",
        "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 'OSWorld-Verified', column 'Muse Spark'"
          }
        ],
        "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:terminal-bench-2-1:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 67.3,
        "unit": "%",
        "printed": "67.3",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark",
        "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": "Muse Spark 1.1 benchmark table (image), row 'Terminal-Bench 2.1', column 'Muse Spark'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "",
        "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": "67.3",
            "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 'Terminal-Bench 2.1', column 'Muse Spark'"
          }
        ],
        "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:deepswe-1-1:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 10.0,
        "unit": "%",
        "printed": "10.0",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark",
        "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": "Muse Spark 1.1 benchmark table (image), row 'DeepSWE 1.1', column 'Muse Spark'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "",
        "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": "10.0",
            "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 'DeepSWE 1.1', column 'Muse Spark'"
          }
        ],
        "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:swe-bench-pro:default:2",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "swe-bench-pro",
        "benchmark_name": "SWE-bench Pro",
        "setting": "default",
        "setting_name": "",
        "score": 55.0,
        "unit": "%",
        "printed": "55.0",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark",
        "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": "Muse Spark 1.1 benchmark table (image), row 'SWE-Bench Pro', column 'Muse Spark'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "",
        "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": "55.0",
            "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 'SWE-Bench Pro', column 'Muse Spark'"
          }
        ],
        "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:mcp-atlas:default:1",
        "model": "muse-spark",
        "model_name": "Muse Spark",
        "model_date": "2026-04-08",
        "event": "https://frontierlog.ai/event/2026-04-08-muse-spark",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "default",
        "setting_name": "",
        "score": 82.2,
        "unit": "%",
        "printed": "82.2",
        "reported_by": "meta",
        "run_by": null,
        "label": "Muse Spark",
        "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": "Muse Spark 1.1 benchmark table (image), row 'MCP Atlas', column 'Muse Spark'",
        "own": false,
        "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"
      }
    ]
  }
}