{
  "apiVersion": "1",
  "methodologyVersion": "2026-07-09-gso-ml-domain",
  "updatedAt": "2026-07-13T21:57:32.936Z",
  "rankings": [
    {
      "id": "composite-iq",
      "rankingName": "Composite IQ",
      "rankingType": "derived",
      "dimension": null,
      "direction": "higher_is_better",
      "modelCount": 91,
      "url": "https://www.aiiq.org/api/rankings/composite-iq"
    },
    {
      "id": "effective-cost",
      "rankingName": "Effective Cost",
      "rankingType": "derived",
      "dimension": null,
      "direction": "lower_is_better",
      "modelCount": 89,
      "url": "https://www.aiiq.org/api/rankings/effective-cost"
    },
    {
      "id": "abstract-reasoning-iq",
      "rankingName": "Abstract Reasoning IQ",
      "rankingType": "dimension",
      "dimension": "abstract-reasoning",
      "direction": "higher_is_better",
      "modelCount": 102,
      "url": "https://www.aiiq.org/api/rankings/abstract-reasoning-iq"
    },
    {
      "id": "mathematical-reasoning-iq",
      "rankingName": "Mathematical Reasoning IQ",
      "rankingType": "dimension",
      "dimension": "mathematical-reasoning",
      "direction": "higher_is_better",
      "modelCount": 103,
      "url": "https://www.aiiq.org/api/rankings/mathematical-reasoning-iq"
    },
    {
      "id": "scientific-reasoning-iq",
      "rankingName": "Scientific Reasoning IQ",
      "rankingType": "dimension",
      "dimension": "scientific-reasoning",
      "direction": "higher_is_better",
      "modelCount": 103,
      "url": "https://www.aiiq.org/api/rankings/scientific-reasoning-iq"
    },
    {
      "id": "frontend-engineering-iq",
      "rankingName": "Frontend Engineering IQ",
      "rankingType": "dimension",
      "dimension": "frontend-engineering",
      "direction": "higher_is_better",
      "modelCount": 91,
      "url": "https://www.aiiq.org/api/rankings/frontend-engineering-iq"
    },
    {
      "id": "backend-engineering-iq",
      "rankingName": "Backend Engineering IQ",
      "rankingType": "dimension",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 97,
      "url": "https://www.aiiq.org/api/rankings/backend-engineering-iq"
    },
    {
      "id": "computer-use-iq",
      "rankingName": "Computer Use IQ",
      "rankingType": "dimension",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 95,
      "url": "https://www.aiiq.org/api/rankings/computer-use-iq"
    },
    {
      "id": "reliability-iq",
      "rankingName": "Reliability IQ",
      "rankingType": "dimension",
      "dimension": "reliability",
      "direction": "higher_is_better",
      "modelCount": 97,
      "url": "https://www.aiiq.org/api/rankings/reliability-iq"
    },
    {
      "id": "aa-lcr",
      "rankingName": "AA Long Chain Reasoning",
      "rankingType": "benchmark",
      "dimension": "reliability",
      "direction": "higher_is_better",
      "modelCount": 90,
      "url": "https://www.aiiq.org/api/rankings/aa-lcr"
    },
    {
      "id": "aa-omniscience",
      "rankingName": "AA Omniscience",
      "rankingType": "benchmark",
      "dimension": "reliability",
      "direction": "higher_is_better",
      "modelCount": 87,
      "url": "https://www.aiiq.org/api/rankings/aa-omniscience"
    },
    {
      "id": "agents-last-exam",
      "rankingName": "Agents' Last Exam",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 15,
      "url": "https://www.aiiq.org/api/rankings/agents-last-exam"
    },
    {
      "id": "aime",
      "rankingName": "AIME",
      "rankingType": "benchmark",
      "dimension": "mathematical-reasoning",
      "direction": "higher_is_better",
      "modelCount": 53,
      "url": "https://www.aiiq.org/api/rankings/aime"
    },
    {
      "id": "apex-swe",
      "rankingName": "APEX-SWE",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 19,
      "url": "https://www.aiiq.org/api/rankings/apex-swe"
    },
    {
      "id": "arc-agi-1",
      "rankingName": "ARC-AGI-1",
      "rankingType": "benchmark",
      "dimension": "abstract-reasoning",
      "direction": "higher_is_better",
      "modelCount": 37,
      "url": "https://www.aiiq.org/api/rankings/arc-agi-1"
    },
    {
      "id": "arc-agi-2",
      "rankingName": "ARC-AGI-2",
      "rankingType": "benchmark",
      "dimension": "abstract-reasoning",
      "direction": "higher_is_better",
      "modelCount": 37,
      "url": "https://www.aiiq.org/api/rankings/arc-agi-2"
    },
    {
      "id": "arc-agi-3",
      "rankingName": "ARC-AGI-3",
      "rankingType": "benchmark",
      "dimension": "abstract-reasoning",
      "direction": "higher_is_better",
      "modelCount": 10,
      "url": "https://www.aiiq.org/api/rankings/arc-agi-3"
    },
    {
      "id": "arena-score",
      "rankingName": "Arena.ai Overall",
      "rankingType": "benchmark",
      "dimension": null,
      "direction": "higher_is_better",
      "modelCount": 64,
      "url": "https://www.aiiq.org/api/rankings/arena-score"
    },
    {
      "id": "attunebench-composite",
      "rankingName": "AttuneBench Composite",
      "rankingType": "benchmark",
      "dimension": null,
      "direction": "higher_is_better",
      "modelCount": 11,
      "url": "https://www.aiiq.org/api/rankings/attunebench-composite"
    },
    {
      "id": "browsecomp",
      "rankingName": "BrowseComp",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 24,
      "url": "https://www.aiiq.org/api/rankings/browsecomp"
    },
    {
      "id": "bullshitbench-v2",
      "rankingName": "BullshitBench v2",
      "rankingType": "benchmark",
      "dimension": "reliability",
      "direction": "higher_is_better",
      "modelCount": 57,
      "url": "https://www.aiiq.org/api/rankings/bullshitbench-v2"
    },
    {
      "id": "critpt",
      "rankingName": "CritPt",
      "rankingType": "benchmark",
      "dimension": "scientific-reasoning",
      "direction": "higher_is_better",
      "modelCount": 93,
      "url": "https://www.aiiq.org/api/rankings/critpt"
    },
    {
      "id": "deepswe-v1-1",
      "rankingName": "DeepSWE v1.1",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 10,
      "url": "https://www.aiiq.org/api/rankings/deepswe-v1-1"
    },
    {
      "id": "deepswe",
      "rankingName": "DeepSWE",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 18,
      "url": "https://www.aiiq.org/api/rankings/deepswe"
    },
    {
      "id": "designarena-frontend",
      "rankingName": "DesignArena Frontend",
      "rankingType": "benchmark",
      "dimension": "frontend-engineering",
      "direction": "higher_is_better",
      "modelCount": 18,
      "url": "https://www.aiiq.org/api/rankings/designarena-frontend"
    },
    {
      "id": "designarena-fullstack",
      "rankingName": "DesignArena Full Stack",
      "rankingType": "benchmark",
      "dimension": "frontend-engineering",
      "direction": "higher_is_better",
      "modelCount": 20,
      "url": "https://www.aiiq.org/api/rankings/designarena-fullstack"
    },
    {
      "id": "eq-bench-3-elo",
      "rankingName": "EQ-Bench 3 Elo",
      "rankingType": "benchmark",
      "dimension": null,
      "direction": "higher_is_better",
      "modelCount": 30,
      "url": "https://www.aiiq.org/api/rankings/eq-bench-3-elo"
    },
    {
      "id": "facts-grounding",
      "rankingName": "FACTS Grounding",
      "rankingType": "benchmark",
      "dimension": "reliability",
      "direction": "higher_is_better",
      "modelCount": 24,
      "url": "https://www.aiiq.org/api/rankings/facts-grounding"
    },
    {
      "id": "frontiercode-diamond",
      "rankingName": "FrontierCode Diamond",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 12,
      "url": "https://www.aiiq.org/api/rankings/frontiercode-diamond"
    },
    {
      "id": "frontiermath-t13",
      "rankingName": "FrontierMath Tier 1-3",
      "rankingType": "benchmark",
      "dimension": "mathematical-reasoning",
      "direction": "higher_is_better",
      "modelCount": 35,
      "url": "https://www.aiiq.org/api/rankings/frontiermath-t13"
    },
    {
      "id": "frontiermath-t4",
      "rankingName": "FrontierMath Tier 4",
      "rankingType": "benchmark",
      "dimension": "mathematical-reasoning",
      "direction": "higher_is_better",
      "modelCount": 32,
      "url": "https://www.aiiq.org/api/rankings/frontiermath-t4"
    },
    {
      "id": "frontierswe",
      "rankingName": "FrontierSWE",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 13,
      "url": "https://www.aiiq.org/api/rankings/frontierswe"
    },
    {
      "id": "gpqa-diamond",
      "rankingName": "GPQA Diamond",
      "rankingType": "benchmark",
      "dimension": "scientific-reasoning",
      "direction": "higher_is_better",
      "modelCount": 101,
      "url": "https://www.aiiq.org/api/rankings/gpqa-diamond"
    },
    {
      "id": "humanitys-last-exam",
      "rankingName": "Humanity's Last Exam",
      "rankingType": "benchmark",
      "dimension": "scientific-reasoning",
      "direction": "higher_is_better",
      "modelCount": 101,
      "url": "https://www.aiiq.org/api/rankings/humanitys-last-exam"
    },
    {
      "id": "ifbench",
      "rankingName": "IFBench",
      "rankingType": "benchmark",
      "dimension": "reliability",
      "direction": "higher_is_better",
      "modelCount": 86,
      "url": "https://www.aiiq.org/api/rankings/ifbench"
    },
    {
      "id": "livecodebench",
      "rankingName": "LiveCodeBench",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 53,
      "url": "https://www.aiiq.org/api/rankings/livecodebench"
    },
    {
      "id": "matharena",
      "rankingName": "MathArena",
      "rankingType": "benchmark",
      "dimension": "mathematical-reasoning",
      "direction": "higher_is_better",
      "modelCount": 35,
      "url": "https://www.aiiq.org/api/rankings/matharena"
    },
    {
      "id": "mcp-atlas",
      "rankingName": "MCP Atlas",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 21,
      "url": "https://www.aiiq.org/api/rankings/mcp-atlas"
    },
    {
      "id": "osworld-verified",
      "rankingName": "OSWorld-Verified",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 14,
      "url": "https://www.aiiq.org/api/rankings/osworld-verified"
    },
    {
      "id": "proofbench",
      "rankingName": "ProofBench",
      "rankingType": "benchmark",
      "dimension": "mathematical-reasoning",
      "direction": "higher_is_better",
      "modelCount": 33,
      "url": "https://www.aiiq.org/api/rankings/proofbench"
    },
    {
      "id": "scicode",
      "rankingName": "SciCode",
      "rankingType": "benchmark",
      "dimension": "scientific-reasoning",
      "direction": "higher_is_better",
      "modelCount": 101,
      "url": "https://www.aiiq.org/api/rankings/scicode"
    },
    {
      "id": "swe-marathon",
      "rankingName": "SWE Marathon",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 10,
      "url": "https://www.aiiq.org/api/rankings/swe-marathon"
    },
    {
      "id": "swe-rebench",
      "rankingName": "SWE-rebench",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 12,
      "url": "https://www.aiiq.org/api/rankings/swe-rebench"
    },
    {
      "id": "swebench-pro",
      "rankingName": "SWE-Bench Pro",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 20,
      "url": "https://www.aiiq.org/api/rankings/swebench-pro"
    },
    {
      "id": "swebench-verified",
      "rankingName": "SWE-Bench Verified",
      "rankingType": "benchmark",
      "dimension": "backend-engineering",
      "direction": "higher_is_better",
      "modelCount": 63,
      "url": "https://www.aiiq.org/api/rankings/swebench-verified"
    },
    {
      "id": "terminal-bench-2-1",
      "rankingName": "Terminal-Bench 2.1",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 57,
      "url": "https://www.aiiq.org/api/rankings/terminal-bench-2-1"
    },
    {
      "id": "terminal-bench-hard",
      "rankingName": "Terminal-Bench Hard",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 78,
      "url": "https://www.aiiq.org/api/rankings/terminal-bench-hard"
    },
    {
      "id": "toolathlon",
      "rankingName": "Toolathlon",
      "rankingType": "benchmark",
      "dimension": "computer-use",
      "direction": "higher_is_better",
      "modelCount": 20,
      "url": "https://www.aiiq.org/api/rankings/toolathlon"
    },
    {
      "id": "vibe-code-bench",
      "rankingName": "Vibe Code Bench",
      "rankingType": "benchmark",
      "dimension": "frontend-engineering",
      "direction": "higher_is_better",
      "modelCount": 49,
      "url": "https://www.aiiq.org/api/rankings/vibe-code-bench"
    },
    {
      "id": "webdev-code-arena",
      "rankingName": "Arena.ai WebDev",
      "rankingType": "benchmark",
      "dimension": "frontend-engineering",
      "direction": "higher_is_better",
      "modelCount": 58,
      "url": "https://www.aiiq.org/api/rankings/webdev-code-arena"
    }
  ]
}