{
  "title": "Unbind Flash V1 benchmark comparison",
  "source": "Data supplied by UnbindAI in this chat; no external verification requested or performed.",
  "asterisk_note": "Asterisks are preserved exactly as supplied. Their meaning was not specified.",
  "benchmarks": [
    {
      "id": "01-aa-index-v5",
      "name": "AA Index v5",
      "short": [
        "AA Index",
        "v5"
      ],
      "kind": "Index points"
    },
    {
      "id": "02-hle-diamond",
      "name": "HLE-Diamond",
      "short": [
        "HLE-",
        "Diamond"
      ],
      "kind": "Reported score"
    },
    {
      "id": "03-gpqa-diamond",
      "name": "GPQA Diamond",
      "short": [
        "GPQA",
        "Diamond"
      ],
      "kind": "Reported score"
    },
    {
      "id": "04-terminal-bench-4",
      "name": "Terminal-Bench 4",
      "short": [
        "Terminal-",
        "Bench 4"
      ],
      "kind": "Reported score"
    },
    {
      "id": "05-frontiercode-2",
      "name": "FrontierCode 2",
      "short": [
        "FrontierCode",
        "2"
      ],
      "kind": "Reported score"
    },
    {
      "id": "06-livebench-2",
      "name": "LiveBench 2",
      "short": [
        "LiveBench",
        "2"
      ],
      "kind": "Reported score"
    },
    {
      "id": "07-livecodebench",
      "name": "LiveCodeBench",
      "short": [
        "LiveCodeBench"
      ],
      "kind": "Reported score"
    }
  ],
  "models": [
    {
      "name": "Claude Opus 5",
      "scores": [
        "45.0*",
        "49.0*",
        "93.9",
        "49.0",
        "35.0*",
        "78.0*",
        "89.0"
      ]
    },
    {
      "name": "GPT-5.6 Sol",
      "scores": [
        "39.5*",
        "40.0*",
        "93.5",
        "39.9",
        "28.0*",
        "73.0*",
        "82.6"
      ]
    },
    {
      "name": "GPT-6 Sol",
      "scores": [
        "43.0*",
        "45.2",
        "94.3",
        "43.9",
        "32.0*",
        "77.0*",
        "87.0*"
      ]
    },
    {
      "name": "Claude Sonnet 5",
      "scores": [
        "30.0*",
        "30.0*",
        "80.3",
        "14.1",
        "20.0*",
        "68.0*",
        "82.4"
      ]
    },
    {
      "name": "GPT-5.6 Terra",
      "scores": [
        "34.0*",
        "28.8",
        "93.3",
        "35.4",
        "25.0*",
        "67.8",
        "85.9"
      ]
    },
    {
      "name": "Gemini 3.1 Pro",
      "scores": [
        "30.0*",
        "31.4",
        "94.4",
        "4.0",
        "18.0*",
        "69.0*",
        "88.5"
      ]
    },
    {
      "name": "Muse Spark 1.3",
      "scores": [
        "36.4",
        "33.7",
        "93.5",
        "33.3",
        "23.1",
        "63.0",
        "85.0*"
      ]
    },
    {
      "name": "Claude Fable 5",
      "scores": [
        "38.0*",
        "45.0*",
        "85.9",
        "42.4",
        "30.0*",
        "76.0*",
        "89.8"
      ]
    },
    {
      "name": "Unbind Flash V1",
      "scores": [
        "31.0*",
        "26.9",
        "93.1",
        "12.6",
        "10.9",
        "64.6",
        "87.2"
      ]
    }
  ],
  "reported_test_result": {
    "passed": 320,
    "total": 320,
    "source": "Reported by UnbindAI",
    "suite_name": null,
    "pass_criteria": null,
    "raw_logs_supplied": false
  }
}