{
  "apiVersion": "1",
  "methodologyVersion": "2026-09-30-arc-predictive-puzzles",
  "updatedAt": "2026-10-13T12:11:32.230Z",
  "charts": [
    {
      "id": "iq-bell-curve",
      "title": "IQ Bell Curve",
      "description": "Each model's estimated IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/iq-bell-curve/",
      "image": "https://www.aiiq.org/og/charts/iq-bell-curve.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "bellCurve"
      ]
    },
    {
      "id": "iq-scores",
      "title": "IQ Rankings",
      "description": "Each model's estimated IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/iq-scores/",
      "image": "https://www.aiiq.org/og/charts/iq-scores.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "benchmarkBar"
      ]
    },
    {
      "id": "frontier-iq-over-time",
      "title": "IQ Over Time",
      "description": "Each model's estimated IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/frontier-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/frontier-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "timeline"
      ]
    },
    {
      "id": "iq-vs-eq",
      "title": "IQ vs EQ",
      "description": "X = diagnostic EQ. Y = IQ. Color = model provider.",
      "url": "https://www.aiiq.org/charts/iq-vs-eq/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-eq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "color"
      ]
    },
    {
      "id": "iq-eq-cost-3d",
      "title": "IQ vs EQ vs Cost in 3D",
      "description": "3D scatter: X = diagnostic EQ, Y = IQ, Z = effective cost (log). Color = provider. Drag to rotate.",
      "url": "https://www.aiiq.org/charts/iq-eq-cost-3d/",
      "image": "https://www.aiiq.org/og/charts/iq-eq-cost-3d.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "3d"
      ]
    },
    {
      "id": "ai-models-by-country-over-time",
      "title": "AI Models by Country Over Time",
      "description": "Each bar counts the AI models AI IQ tracks that had been released by that month, stacked by the country of their developer.",
      "url": "https://www.aiiq.org/charts/ai-models-by-country-over-time/",
      "image": "https://www.aiiq.org/og/charts/ai-models-by-country-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "countryStack"
      ]
    },
    {
      "id": "ai-model-share-by-country-over-time",
      "title": "AI Model Share by Country Over Time",
      "description": "The national origin of tracked AI models as a share of the total — each month normalized to 100%, so the changing balance between countries is easy to read.",
      "url": "https://www.aiiq.org/charts/ai-model-share-by-country-over-time/",
      "image": "https://www.aiiq.org/og/charts/ai-model-share-by-country-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Core",
        "countryStack"
      ]
    },
    {
      "id": "abstract-reasoning-iq",
      "title": "Abstract Reasoning IQ Bell Curve",
      "description": "Each model's estimated Abstract Reasoning IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/abstract-reasoning-iq/",
      "image": "https://www.aiiq.org/og/charts/abstract-reasoning-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "mathematical-reasoning-iq",
      "title": "Mathematical Reasoning IQ Bell Curve",
      "description": "Each model's estimated Mathematical Reasoning IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/mathematical-reasoning-iq/",
      "image": "https://www.aiiq.org/og/charts/mathematical-reasoning-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "academic-reasoning-iq",
      "title": "Academic Reasoning IQ Bell Curve",
      "description": "Each model's estimated Academic Reasoning IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/academic-reasoning-iq/",
      "image": "https://www.aiiq.org/og/charts/academic-reasoning-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "programmatic-reasoning-iq",
      "title": "Programmatic Reasoning IQ Bell Curve",
      "description": "Each model's estimated Programmatic Reasoning IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/programmatic-reasoning-iq/",
      "image": "https://www.aiiq.org/og/charts/programmatic-reasoning-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "computer-use-iq",
      "title": "Computer Use IQ Bell Curve",
      "description": "Each model's estimated Computer Use IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/computer-use-iq/",
      "image": "https://www.aiiq.org/og/charts/computer-use-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "reliability-iq",
      "title": "Reliability IQ Bell Curve",
      "description": "Each model's estimated Reliability IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/reliability-iq/",
      "image": "https://www.aiiq.org/og/charts/reliability-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "knowledge-work-iq",
      "title": "Knowledge Work IQ Bell Curve",
      "description": "Each model's estimated Knowledge Work IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/knowledge-work-iq/",
      "image": "https://www.aiiq.org/og/charts/knowledge-work-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "emotional-reasoning-eq",
      "title": "Emotional Reasoning IQ Bell Curve",
      "description": "Each model's Emotional Reasoning IQ, derived from EQ-Bench 4 and AttuneBench and excluded from Composite IQ, placed on a standard normal IQ distribution.",
      "url": "https://www.aiiq.org/charts/emotional-reasoning-eq/",
      "image": "https://www.aiiq.org/og/charts/emotional-reasoning-eq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Emotional & Interaction",
        "bellCurve"
      ]
    },
    {
      "id": "arc-agi-3-scores",
      "title": "ARC-AGI-3 Benchmark Scores",
      "description": "Each model's ARC-AGI-3 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/arc-agi-3-scores/",
      "image": "https://www.aiiq.org/og/charts/arc-agi-3-scores.png",
      "relatedBenchmarks": [
        "arc-agi-3"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "arc-agi-2-scores",
      "title": "ARC-AGI-2 Scores",
      "description": "Each model's ARC-AGI-2 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/arc-agi-2-scores/",
      "image": "https://www.aiiq.org/og/charts/arc-agi-2-scores.png",
      "relatedBenchmarks": [
        "arc-agi-2"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "arc-agi-1-scores",
      "title": "ARC-AGI-1 Benchmark Scores",
      "description": "Each model's ARC-AGI-1 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/arc-agi-1-scores/",
      "image": "https://www.aiiq.org/og/charts/arc-agi-1-scores.png",
      "relatedBenchmarks": [
        "arc-agi-1"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "frontiermath-tier-4-scores",
      "title": "FrontierMath Tier 4 Benchmark Scores",
      "description": "Each model's FrontierMath Tier 4 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/frontiermath-tier-4-scores/",
      "image": "https://www.aiiq.org/og/charts/frontiermath-tier-4-scores.png",
      "relatedBenchmarks": [
        "frontiermath-t4"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "frontiermath-tier-1-3-scores",
      "title": "FrontierMath Tier 1-3 Benchmark Scores",
      "description": "Each model's FrontierMath Tier 1-3 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/frontiermath-tier-1-3-scores/",
      "image": "https://www.aiiq.org/og/charts/frontiermath-tier-1-3-scores.png",
      "relatedBenchmarks": [
        "frontiermath-t13"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "matharena-scores",
      "title": "MathArena Benchmark Scores",
      "description": "Each model's MathArena expected performance. Color = provider.",
      "url": "https://www.aiiq.org/charts/matharena-scores/",
      "image": "https://www.aiiq.org/og/charts/matharena-scores.png",
      "relatedBenchmarks": [
        "matharena"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "aime-scores",
      "title": "AIME Benchmark Scores",
      "description": "Each model's AIME score. Color = provider.",
      "url": "https://www.aiiq.org/charts/aime-scores/",
      "image": "https://www.aiiq.org/og/charts/aime-scores.png",
      "relatedBenchmarks": [
        "aime"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "webdev-code-arena-scores",
      "title": "Arena.ai WebDev Scores",
      "description": "Arena.ai WebDev Elo scores for front-end web development. Color = provider.",
      "url": "https://www.aiiq.org/charts/webdev-code-arena-scores/",
      "image": "https://www.aiiq.org/og/charts/webdev-code-arena-scores.png",
      "relatedBenchmarks": [
        "webdev-code-arena"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "designarena-frontend-scores",
      "title": "DesignArena Frontend Scores",
      "description": "DesignArena Frontend Elo for agentic front-end web apps. Color = provider.",
      "url": "https://www.aiiq.org/charts/designarena-frontend-scores/",
      "image": "https://www.aiiq.org/og/charts/designarena-frontend-scores.png",
      "relatedBenchmarks": [
        "designarena-frontend"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "designarena-fullstack-scores",
      "title": "DesignArena Full Stack Scores",
      "description": "DesignArena Full Stack Elo for end-to-end frontend + backend builds. Color = provider.",
      "url": "https://www.aiiq.org/charts/designarena-fullstack-scores/",
      "image": "https://www.aiiq.org/og/charts/designarena-fullstack-scores.png",
      "relatedBenchmarks": [
        "designarena-fullstack"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "vibe-code-bench-scores",
      "title": "Vibe Code Bench v1.1 Scores",
      "description": "Vals.ai Vibe Code Bench v1.1 accuracy for building web applications from scratch. Color = provider.",
      "url": "https://www.aiiq.org/charts/vibe-code-bench-scores/",
      "image": "https://www.aiiq.org/og/charts/vibe-code-bench-scores.png",
      "relatedBenchmarks": [
        "vibe-code-bench"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "swe-marathon-scores",
      "title": "SWE Marathon Scores",
      "description": "Each model's SWE Marathon aggregate Resolution Rate (Pass@1). Color = provider.",
      "url": "https://www.aiiq.org/charts/swe-marathon-scores/",
      "image": "https://www.aiiq.org/og/charts/swe-marathon-scores.png",
      "relatedBenchmarks": [
        "swe-marathon"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "apex-swe-scores",
      "title": "APEX-SWE Scores",
      "description": "Mercor APEX-SWE overall Pass@1 scores for economically valuable software-engineering work. Color = provider.",
      "url": "https://www.aiiq.org/charts/apex-swe-scores/",
      "image": "https://www.aiiq.org/og/charts/apex-swe-scores.png",
      "relatedBenchmarks": [
        "apex-swe"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "gso-bench-scores",
      "title": "GSO-Bench Scores",
      "description": "Each model's GSO Opt@1 score for software optimization tasks. Color = provider.",
      "url": "https://www.aiiq.org/charts/gso-bench-scores/",
      "image": "https://www.aiiq.org/og/charts/gso-bench-scores.png",
      "relatedBenchmarks": [
        "gso-bench"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "frontiercode-diamond-scores",
      "title": "FrontierCode Diamond Scores",
      "description": "Each model's FrontierCode Diamond score for high-quality production-code tasks. Color = provider.",
      "url": "https://www.aiiq.org/charts/frontiercode-diamond-scores/",
      "image": "https://www.aiiq.org/og/charts/frontiercode-diamond-scores.png",
      "relatedBenchmarks": [
        "frontiercode-diamond"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "swe-rebench-scores",
      "title": "SWE-rebench Benchmark Scores",
      "description": "Each model's SWE-rebench resolved rate. Color = provider.",
      "url": "https://www.aiiq.org/charts/swe-rebench-scores/",
      "image": "https://www.aiiq.org/og/charts/swe-rebench-scores.png",
      "relatedBenchmarks": [
        "swe-rebench"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "deepswe-v1-1-scores",
      "title": "DeepSWE v1.1 Benchmark Scores",
      "description": "Each model's DeepSWE v1.1 Pass@1 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/deepswe-v1-1-scores/",
      "image": "https://www.aiiq.org/og/charts/deepswe-v1-1-scores.png",
      "relatedBenchmarks": [
        "deepswe-v1-1"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "kernelbench-hard-scores",
      "title": "KernelBench Hard Benchmark Scores",
      "description": "Each model's audited KernelBench Hard pass rate. Color = provider.",
      "url": "https://www.aiiq.org/charts/kernelbench-hard-scores/",
      "image": "https://www.aiiq.org/og/charts/kernelbench-hard-scores.png",
      "relatedBenchmarks": [
        "kernelbench-hard"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "kernelbench-mega-scores",
      "title": "KernelBench Mega Benchmark Scores",
      "description": "Each model's RTX PRO 6000 KernelBench Mega speedup over optimized PyTorch. Color = provider.",
      "url": "https://www.aiiq.org/charts/kernelbench-mega-scores/",
      "image": "https://www.aiiq.org/og/charts/kernelbench-mega-scores.png",
      "relatedBenchmarks": [
        "kernelbench-mega"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "swe-bench-pro-scores",
      "title": "SWE-Bench Pro Benchmark Scores",
      "description": "Each model's SWE-Bench Pro percentage score. Color = provider.",
      "url": "https://www.aiiq.org/charts/swe-bench-pro-scores/",
      "image": "https://www.aiiq.org/og/charts/swe-bench-pro-scores.png",
      "relatedBenchmarks": [
        "swebench-pro"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "livecodebench-scores",
      "title": "LiveCodeBench Benchmark Scores",
      "description": "Each model's LiveCodeBench score. Color = provider.",
      "url": "https://www.aiiq.org/charts/livecodebench-scores/",
      "image": "https://www.aiiq.org/og/charts/livecodebench-scores.png",
      "relatedBenchmarks": [
        "livecodebench"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "programbench-almost-resolved-scores",
      "title": "ProgramBench Scores",
      "description": "Almost Resolved score: share of ProgramBench tasks passing at least 95% of hidden tests. Color = provider.",
      "url": "https://www.aiiq.org/charts/programbench-almost-resolved-scores/",
      "image": "https://www.aiiq.org/og/charts/programbench-almost-resolved-scores.png",
      "relatedBenchmarks": [
        "programbench-almost-resolved"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "scicode-scores",
      "title": "SciCode Benchmark Scores",
      "description": "Each model's SciCode score. Color = provider.",
      "url": "https://www.aiiq.org/charts/scicode-scores/",
      "image": "https://www.aiiq.org/og/charts/scicode-scores.png",
      "relatedBenchmarks": [
        "scicode"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "critpt-scores",
      "title": "CritPt Benchmark Scores",
      "description": "Each model's CritPt percentage score. Color = provider.",
      "url": "https://www.aiiq.org/charts/critpt-scores/",
      "image": "https://www.aiiq.org/og/charts/critpt-scores.png",
      "relatedBenchmarks": [
        "critpt"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "humanitys-last-exam-scores",
      "title": "Humanity's Last Exam Benchmark Scores",
      "description": "Each model's Humanity's Last Exam score. Color = provider.",
      "url": "https://www.aiiq.org/charts/humanitys-last-exam-scores/",
      "image": "https://www.aiiq.org/og/charts/humanitys-last-exam-scores.png",
      "relatedBenchmarks": [
        "humanitys-last-exam"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "gpqa-diamond-scores",
      "title": "GPQA Diamond Benchmark Scores",
      "description": "Each model's GPQA Diamond score. Color = provider.",
      "url": "https://www.aiiq.org/charts/gpqa-diamond-scores/",
      "image": "https://www.aiiq.org/og/charts/gpqa-diamond-scores.png",
      "relatedBenchmarks": [
        "gpqa-diamond"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "mmlu-pro-scores",
      "title": "MMLU-Pro Benchmark Scores",
      "description": "Each model's MMLU-Pro score. Color = provider.",
      "url": "https://www.aiiq.org/charts/mmlu-pro-scores/",
      "image": "https://www.aiiq.org/og/charts/mmlu-pro-scores.png",
      "relatedBenchmarks": [
        "mmlu-pro"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "mmmu-pro-scores",
      "title": "MMMU-Pro Benchmark Scores",
      "description": "Each model's MMMU-Pro score. Color = provider.",
      "url": "https://www.aiiq.org/charts/mmmu-pro-scores/",
      "image": "https://www.aiiq.org/og/charts/mmmu-pro-scores.png",
      "relatedBenchmarks": [
        "mmmu-pro"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "browsecomp-scores",
      "title": "BrowseComp Benchmark Scores",
      "description": "Each model's BrowseComp score. Color = provider.",
      "url": "https://www.aiiq.org/charts/browsecomp-scores/",
      "image": "https://www.aiiq.org/og/charts/browsecomp-scores.png",
      "relatedBenchmarks": [
        "browsecomp"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "osworld-verified-scores",
      "title": "OSWorld-Verified Benchmark Scores",
      "description": "Each model's OSWorld-Verified score. Color = provider.",
      "url": "https://www.aiiq.org/charts/osworld-verified-scores/",
      "image": "https://www.aiiq.org/og/charts/osworld-verified-scores.png",
      "relatedBenchmarks": [
        "osworld-verified"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "mcp-atlas-scores",
      "title": "MCP Atlas Benchmark Scores",
      "description": "Real-world MCP tool-use pass rates. Color = provider.",
      "url": "https://www.aiiq.org/charts/mcp-atlas-scores/",
      "image": "https://www.aiiq.org/og/charts/mcp-atlas-scores.png",
      "relatedBenchmarks": [
        "mcp-atlas"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "agents-last-exam-scores",
      "title": "Agents' Last Exam Benchmark Scores",
      "description": "Full / Overall pass rates from Agents' Last Exam. Color = provider.",
      "url": "https://www.aiiq.org/charts/agents-last-exam-scores/",
      "image": "https://www.aiiq.org/og/charts/agents-last-exam-scores.png",
      "relatedBenchmarks": [
        "agents-last-exam"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "agent-arena-scores",
      "title": "Arena.ai Agent Arena Scores",
      "description": "Aggregate net improvement across real-world Agent Mode sessions. Color = provider.",
      "url": "https://www.aiiq.org/charts/agent-arena-scores/",
      "image": "https://www.aiiq.org/og/charts/agent-arena-scores.png",
      "relatedBenchmarks": [
        "agent-arena"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "ifbench-scores",
      "title": "IFBench Benchmark Scores",
      "description": "Instruction-following and constraint-adherence scores. Color = provider.",
      "url": "https://www.aiiq.org/charts/ifbench-scores/",
      "image": "https://www.aiiq.org/og/charts/ifbench-scores.png",
      "relatedBenchmarks": [
        "ifbench"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "aa-omniscience-scores",
      "title": "AA Omniscience Scores",
      "description": "Artificial Analysis Omniscience scores for factual reliability. Color = provider.",
      "url": "https://www.aiiq.org/charts/aa-omniscience-scores/",
      "image": "https://www.aiiq.org/og/charts/aa-omniscience-scores.png",
      "relatedBenchmarks": [
        "aa-omniscience"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "bullshitbench-v2-scores",
      "title": "BullshitBench v2 Scores",
      "description": "Clear Pushback rate: share of attempts where a model clearly challenges a false premise instead of accepting nonsense. Color = provider.",
      "url": "https://www.aiiq.org/charts/bullshitbench-v2-scores/",
      "image": "https://www.aiiq.org/og/charts/bullshitbench-v2-scores.png",
      "relatedBenchmarks": [
        "bullshitbench-v2"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "simpleqa-verified-scores",
      "title": "SimpleQA Verified Scores",
      "description": "Correct-answer rate on Epoch AI's verified factuality set. Color = provider.",
      "url": "https://www.aiiq.org/charts/simpleqa-verified-scores/",
      "image": "https://www.aiiq.org/og/charts/simpleqa-verified-scores.png",
      "relatedBenchmarks": [
        "simpleqa-verified"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "multichallenge-scores",
      "title": "MultiChallenge Scores",
      "description": "Diagnostic multi-turn instruction retention, inference memory, editing, and self-coherence. Does not contribute to IQ. Color = provider.",
      "url": "https://www.aiiq.org/charts/multichallenge-scores/",
      "image": "https://www.aiiq.org/og/charts/multichallenge-scores.png",
      "relatedBenchmarks": [
        "multichallenge"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "facts-grounding-scores",
      "title": "FACTS Grounding Scores",
      "description": "Google FACTS Grounding scores for long-form responses fully grounded in provided documents. Color = provider.",
      "url": "https://www.aiiq.org/charts/facts-grounding-scores/",
      "image": "https://www.aiiq.org/og/charts/facts-grounding-scores.png",
      "relatedBenchmarks": [
        "facts-grounding"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "arena-elo-scores",
      "title": "Arena.ai Overall Benchmark Scores",
      "description": "Human-preference Arena.ai Overall Elo scores. Color = provider.",
      "url": "https://www.aiiq.org/charts/arena-elo-scores/",
      "image": "https://www.aiiq.org/og/charts/arena-elo-scores.png",
      "relatedBenchmarks": [
        "arena-score"
      ],
      "tags": [
        "Emotional & Interaction",
        "benchmarkBar"
      ]
    },
    {
      "id": "eq-bench-3-scores",
      "title": "EQ-Bench 3 Benchmark Scores",
      "description": "AI-judged EQ-Bench 3 Elo, a style-sensitive emotional reasoning signal. Color = provider.",
      "url": "https://www.aiiq.org/charts/eq-bench-3-scores/",
      "image": "https://www.aiiq.org/og/charts/eq-bench-3-scores.png",
      "relatedBenchmarks": [
        "eq-bench-3-elo"
      ],
      "tags": [
        "Emotional & Interaction",
        "benchmarkBar"
      ]
    },
    {
      "id": "attunebench-scores",
      "title": "AttuneBench Benchmark Scores",
      "description": "Default-mode AttuneBench Composite scores from real human-AI conversations. Color = provider.",
      "url": "https://www.aiiq.org/charts/attunebench-scores/",
      "image": "https://www.aiiq.org/og/charts/attunebench-scores.png",
      "relatedBenchmarks": [
        "attunebench-composite"
      ],
      "tags": [
        "Emotional & Interaction",
        "benchmarkBar"
      ]
    },
    {
      "id": "iq-vs-token-cost",
      "title": "IQ vs Input/Output Token Cost",
      "description": "Each model's estimated IQ plotted against its published token price. Toggle between input and output price per 1M tokens.",
      "url": "https://www.aiiq.org/charts/iq-vs-token-cost/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-token-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "xSelectorColor"
      ]
    },
    {
      "id": "iq-vs-task-cost",
      "title": "IQ vs Blended Token Cost",
      "description": "Each model's estimated IQ plotted against the cost of a representative 1M-token blend. Toggle between a coding blend (cache-heavy — 800K cache-read + 100K input + 100K output) and a copywriting blend (output-heavy — 150K input + 850K output).",
      "url": "https://www.aiiq.org/charts/iq-vs-task-cost/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-task-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "xSelectorColor"
      ]
    },
    {
      "id": "iq-vs-effective-cost",
      "title": "IQ vs Cost",
      "description": "Each model's estimated IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "color"
      ]
    },
    {
      "id": "cost-of-intelligence-over-time",
      "title": "The Falling Cost of Intelligence",
      "description": "X = release date. Y = effective cost per 1M I/O Tokens (log). Each step line tracks the cheapest model to date at or above an IQ level; large dots mark the models that set each new price floor, faint dots show every other qualifying model, colored by provider.",
      "url": "https://www.aiiq.org/charts/cost-of-intelligence-over-time/",
      "image": "https://www.aiiq.org/og/charts/cost-of-intelligence-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "costTimeline"
      ]
    },
    {
      "id": "eq-vs-effective-cost",
      "title": "EQ vs Effective Cost",
      "description": "Diagnostic EQ plotted against effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/eq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/eq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "color"
      ]
    },
    {
      "id": "sticker-vs-effective-cost",
      "title": "AI Models by Cost",
      "description": "Published price for 1M I/O Tokens compared with effective cost after applying the measured or imputed task-usage multiplier.",
      "url": "https://www.aiiq.org/charts/sticker-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/sticker-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "costBars"
      ]
    },
    {
      "id": "price-per-1m-tokens",
      "title": "Input Price vs Output Price",
      "description": "Each model positioned by its published token prices — input price (Y) against output price (X), both per 1M tokens on a log scale. The dashed line is the best fit across models, showing the typical output-to-input price relationship.",
      "url": "https://www.aiiq.org/charts/price-per-1m-tokens/",
      "image": "https://www.aiiq.org/og/charts/price-per-1m-tokens.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "color"
      ]
    },
    {
      "id": "task-efficiency",
      "title": "Task Efficiency",
      "description": "Each dot shows the inverse of the effective-cost usage multiplier. Higher means less price-adjusted task work: 2× is about half the median task effort. Source-backed multipliers are preferred; lineage, peer, and 1× fallbacks are labeled in tooltips.",
      "url": "https://www.aiiq.org/charts/task-efficiency/",
      "image": "https://www.aiiq.org/og/charts/task-efficiency.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "tokenEfficiency"
      ]
    },
    {
      "id": "sticker-price-vs-effective-cost",
      "title": "Sticker Price vs Effective Cost",
      "description": "Each model's published sticker price for 1M I/O Tokens plotted against its effective cost after the measured or imputed task-usage multiplier. Points above the dashed line cost more per task than their sticker price suggests.",
      "url": "https://www.aiiq.org/charts/sticker-price-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/sticker-price-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Cost",
        "color"
      ]
    },
    {
      "id": "iq-vs-tokens-per-second",
      "title": "IQ vs Throughput",
      "description": "Throughput is median output tokens per second (TPS). Each model's estimated IQ is plotted against how quickly it streams its answer after generation begins.",
      "url": "https://www.aiiq.org/charts/iq-vs-tokens-per-second/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-tokens-per-second.png",
      "relatedBenchmarks": [
        "aa-median-tps"
      ],
      "tags": [
        "Response Time",
        "color"
      ]
    },
    {
      "id": "iq-vs-time-to-first-token",
      "title": "IQ vs Latency",
      "description": "Latency is time to first token (TTFT): how long a model takes to begin responding. Drag the input-length slider from 1K to 10K tokens to interpolate between AA's two measured TTFT anchors.",
      "url": "https://www.aiiq.org/charts/iq-vs-time-to-first-token/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-time-to-first-token.png",
      "relatedBenchmarks": [],
      "tags": [
        "Response Time",
        "responseLines"
      ]
    },
    {
      "id": "iq-vs-response-time-by-output",
      "title": "IQ vs Speed",
      "description": "Each model's estimated IQ against its completion time, which is time to last token (TTLT). Drag the input (1K–10K tokens) and output (100–10K tokens) sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/iq-vs-response-time-by-output/",
      "image": "https://www.aiiq.org/og/charts/iq-vs-response-time-by-output.png",
      "relatedBenchmarks": [],
      "tags": [
        "Response Time",
        "responseLines"
      ]
    },
    {
      "id": "iq-speed-cost-3d",
      "title": "IQ vs Completion Time vs Cost in 3D",
      "description": "3D scatter: X = completion time (time to last token, TTLT; log, faster to the right), Y = IQ, Z = effective cost (log). Color = provider. Drag to rotate.",
      "url": "https://www.aiiq.org/charts/iq-speed-cost-3d/",
      "image": "https://www.aiiq.org/og/charts/iq-speed-cost-3d.png",
      "relatedBenchmarks": [
        "aa-response-time"
      ],
      "tags": [
        "Response Time",
        "3d"
      ]
    },
    {
      "id": "animated-speed-over-iq-vs-cost",
      "title": "Animating Completion Time over IQ vs Cost",
      "description": "X = Effective Cost/1M I/O Tokens (log). Y = IQ. Clock spin rate represents completion time (time to last token, TTLT).",
      "url": "https://www.aiiq.org/charts/animated-speed-over-iq-vs-cost/",
      "image": "https://www.aiiq.org/og/charts/animated-speed-over-iq-vs-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Response Time",
        "animatedClock"
      ]
    },
    {
      "id": "animated-cost-over-iq-vs-speed",
      "title": "Animating Cost over IQ vs Completion Time",
      "description": "X = completion time (time to last token, TTLT; log, reversed). Y = IQ. Effective Cost/1M I/O Tokens is shown as bills over a 10s period.",
      "url": "https://www.aiiq.org/charts/animated-cost-over-iq-vs-speed/",
      "image": "https://www.aiiq.org/og/charts/animated-cost-over-iq-vs-speed.png",
      "relatedBenchmarks": [
        "aa-response-time"
      ],
      "tags": [
        "Response Time",
        "spend"
      ]
    },
    {
      "id": "ioi-v2-scores",
      "title": "IOI V2 Scores",
      "description": "2024–2026 olympiad tasks, no interactive grading feedback. Version 2 only; separately calibrated from archived V1. Contributes to Programmatic Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/ioi-v2-scores/",
      "image": "https://www.aiiq.org/og/charts/ioi-v2-scores.png",
      "relatedBenchmarks": [
        "ioi-v2"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "proofbench-v1-1-scores",
      "title": "ProofBench 1.1 Scores",
      "description": "Native Lean 4.25.2 verification including native_decide. Version 1.1 only; not comparable to the unversioned historical cohort. Contributes to Mathematical Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/proofbench-v1-1-scores/",
      "image": "https://www.aiiq.org/og/charts/proofbench-v1-1-scores.png",
      "relatedBenchmarks": [
        "proofbench-v1-1"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "code-migration-scores",
      "title": "Code Migration Scores",
      "description": "Full standalone benchmark: 120 CLI migrations across 30 repositories plus 10 COBOL-to-Java repositories, weighted 75/25. Hidden behavioral test pass rate; not the Vals Index subset. Contributes to Software Engineering using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/code-migration-scores/",
      "image": "https://www.aiiq.org/og/charts/code-migration-scores.png",
      "relatedBenchmarks": [
        "code-migration"
      ],
      "tags": [
        "Applied Domain Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "terminal-bench-science-v0-1-scores",
      "title": "Terminal-Bench Science 0.1 (Vals) Scores",
      "description": "All 70 tasks from v0.1.0; fixed Terminus 2 harness, pass@1, eight-hour budget. Infrastructure retries permitted. Not interchangeable with native-agent official scores. Standalone raw result; does not contribute to IQ/EQ.",
      "url": "https://www.aiiq.org/charts/terminal-bench-science-v0-1-scores/",
      "image": "https://www.aiiq.org/og/charts/terminal-bench-science-v0-1-scores.png",
      "relatedBenchmarks": [
        "terminal-bench-science-v0-1"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "tax-agent-bench-scores",
      "title": "Tax Agent Bench Scores",
      "description": "Weighted partial credit over the private 193-question test set, with must-pass checks and citation adjustment. Not the secondary All-Pass metric. Standalone raw result; does not contribute to IQ/EQ.",
      "url": "https://www.aiiq.org/charts/tax-agent-bench-scores/",
      "image": "https://www.aiiq.org/og/charts/tax-agent-bench-scores.png",
      "relatedBenchmarks": [
        "tax-agent-bench"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "vals-index-v2-scores",
      "title": "Vals Index v2 Scores",
      "description": "Version 2 cohort only. Accuracy, cost and latency must come from the same source configuration. Highest published effort; Max and default retained separately in source snapshot. Standalone raw result; does not contribute to IQ/EQ.",
      "url": "https://www.aiiq.org/charts/vals-index-v2-scores/",
      "image": "https://www.aiiq.org/og/charts/vals-index-v2-scores.png",
      "relatedBenchmarks": [
        "vals-index-v2"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "eq-bench-4-elo-scores",
      "title": "EQ-Bench 4 Elo Scores",
      "description": "Published multi-judge Elo on 120 personas and 16 turns. No inherited EQ-Bench 3 Anthropic penalty. Subjective roleplay evaluation; not a validated human EI measure. Contributes to Emotional Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/eq-bench-4-elo-scores/",
      "image": "https://www.aiiq.org/og/charts/eq-bench-4-elo-scores.png",
      "relatedBenchmarks": [
        "eq-bench-4-elo"
      ],
      "tags": [
        "Emotional & Interaction",
        "benchmarkBar"
      ]
    },
    {
      "id": "arxivmath-2026-08-scores",
      "title": "ArXivMath August 2026 Scores",
      "description": "August 2026 release under the September 15 grading revision. Agentic offline harness. Models released after the problems carry source contamination warnings; interpret as diagnostic evidence. Standalone raw result; does not contribute to IQ/EQ.",
      "url": "https://www.aiiq.org/charts/arxivmath-2026-08-scores/",
      "image": "https://www.aiiq.org/og/charts/arxivmath-2026-08-scores.png",
      "relatedBenchmarks": [
        "arxivmath-2026-08"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "brokenarxiv-2026-08-scores",
      "title": "BrokenArXiv August 2026 Scores",
      "description": "August 2026 release under the September 15 grading revision. Agentic offline harness. Models released after the problems carry source contamination warnings; interpret as diagnostic evidence. Standalone raw result; does not contribute to IQ/EQ.",
      "url": "https://www.aiiq.org/charts/brokenarxiv-2026-08-scores/",
      "image": "https://www.aiiq.org/og/charts/brokenarxiv-2026-08-scores.png",
      "relatedBenchmarks": [
        "brokenarxiv-2026-08"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "terminal-bench-4-0-scores",
      "title": "Terminal-Bench 4.0 Scores",
      "description": "Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Programmatic Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/terminal-bench-4-0-scores/",
      "image": "https://www.aiiq.org/og/charts/terminal-bench-4-0-scores.png",
      "relatedBenchmarks": [
        "terminal-bench-4-0"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "aa-lcr-v1-1-scores",
      "title": "AA Long Context Reasoning v1.1 Scores",
      "description": "Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Reliability using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/aa-lcr-v1-1-scores/",
      "image": "https://www.aiiq.org/og/charts/aa-lcr-v1-1-scores.png",
      "relatedBenchmarks": [
        "aa-lcr-v1-1"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "osworld-2-scores",
      "title": "OSWorld 2.0 Scores",
      "description": "Official OSWorld 2.0 leaderboard only: 108 long-horizon desktop tasks, 500-step budget, full task set, binary completion accuracy, best reasoning/tool configuration per model. Partial-credit scores and provider-reported launch figures are excluded. Standalone raw result; does not contribute to IQ/EQ.",
      "url": "https://www.aiiq.org/charts/osworld-2-scores/",
      "image": "https://www.aiiq.org/og/charts/osworld-2-scores.png",
      "relatedBenchmarks": [
        "osworld-2"
      ],
      "tags": [
        "Diagnostic Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "gdpval-aa-v2-scores",
      "title": "GDPval-AA v2.1 normalized score Scores",
      "description": "Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Knowledge Work using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/gdpval-aa-v2-scores/",
      "image": "https://www.aiiq.org/og/charts/gdpval-aa-v2-scores.png",
      "relatedBenchmarks": [
        "gdpval-aa-v2"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "automationbench-aa-scores",
      "title": "AutomationBench-AA Scores",
      "description": "Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Knowledge Work using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/automationbench-aa-scores/",
      "image": "https://www.aiiq.org/og/charts/automationbench-aa-scores.png",
      "relatedBenchmarks": [
        "automationbench-aa"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "gdp-pdf-scores",
      "title": "GDP.pdf Scores",
      "description": "Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Knowledge Work using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/gdp-pdf-scores/",
      "image": "https://www.aiiq.org/og/charts/gdp-pdf-scores.png",
      "relatedBenchmarks": [
        "gdp-pdf"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "aa-briefcase-scores",
      "title": "AA-Briefcase v1.1 Elo Scores",
      "description": "Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Knowledge Work using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/aa-briefcase-scores/",
      "image": "https://www.aiiq.org/og/charts/aa-briefcase-scores.png",
      "relatedBenchmarks": [
        "aa-briefcase"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "mirrorcode-scores",
      "title": "MirrorCode Scores",
      "description": "Epoch ML,+Private,2L: 30 tasks, three repeats, seven days and 10B tokens per attempt. Average rate of completely solved programs; distinct from the paper cohort. Contributes to Programmatic Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/mirrorcode-scores/",
      "image": "https://www.aiiq.org/og/charts/mirrorcode-scores.png",
      "relatedBenchmarks": [
        "mirrorcode"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "aa-analyst-agent-scores",
      "title": "AA-AnalystAgent Scores",
      "description": "Quantitative analysis from spreadsheets and documents. Headline pass^5: correct on every one of five attempts, not pass@5. Contributes to Knowledge Work using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/aa-analyst-agent-scores/",
      "image": "https://www.aiiq.org/og/charts/aa-analyst-agent-scores.png",
      "relatedBenchmarks": [
        "aa-analyst-agent"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "enterprise-ops-gym-aa-scores",
      "title": "EnterpriseOps-Gym-AA Scores",
      "description": "Strict success on 1,117 oracle-mode enterprise workflows, graded against final database state using AA’s Stirrup harness. Contributes to Knowledge Work using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/enterprise-ops-gym-aa-scores/",
      "image": "https://www.aiiq.org/og/charts/enterprise-ops-gym-aa-scores.png",
      "relatedBenchmarks": [
        "enterprise-ops-gym-aa"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "chess-puzzles-scores",
      "title": "Chess Puzzles Scores",
      "description": "Epoch’s 100 novel chess positions, presented as text (FEN). Exact best-next-move accuracy; no vision input. Chess knowledge and planning both contribute. Contributes to Abstract Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/chess-puzzles-scores/",
      "image": "https://www.aiiq.org/og/charts/chess-puzzles-scores.png",
      "relatedBenchmarks": [
        "chess-puzzles"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "mystery-game-puzzles-scores",
      "title": "Mystery Game Puzzles Scores",
      "description": "Epoch’s 100 text-state puzzles in an undisclosed game. Best-next-move accuracy in a minimal agent scaffold; invalid or missing moves receive no credit. Prompts and transcripts are private. Contributes to Abstract Reasoning using a provisional calibrated scale.",
      "url": "https://www.aiiq.org/charts/mystery-game-puzzles-scores/",
      "image": "https://www.aiiq.org/og/charts/mystery-game-puzzles-scores.png",
      "relatedBenchmarks": [
        "mystery-game-puzzles"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "abstract-reasoning-iq-rankings",
      "title": "Abstract Reasoning IQ Rankings",
      "description": "Each model's estimated Abstract Reasoning IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/abstract-reasoning-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/abstract-reasoning-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "abstract-reasoning-iq-vs-completion-time",
      "title": "Abstract Reasoning IQ vs Speed",
      "description": "Each model's estimated Abstract Reasoning IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/abstract-reasoning-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/abstract-reasoning-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "abstract-reasoning-iq-over-time",
      "title": "Abstract Reasoning IQ Over Time",
      "description": "Each model's estimated Abstract Reasoning IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/abstract-reasoning-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/abstract-reasoning-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "mathematical-reasoning-iq-rankings",
      "title": "Mathematical Reasoning IQ Rankings",
      "description": "Each model's estimated Mathematical Reasoning IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/mathematical-reasoning-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/mathematical-reasoning-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "mathematical-reasoning-iq-vs-completion-time",
      "title": "Mathematical Reasoning IQ vs Speed",
      "description": "Each model's estimated Mathematical Reasoning IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/mathematical-reasoning-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/mathematical-reasoning-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "mathematical-reasoning-iq-over-time",
      "title": "Mathematical Reasoning IQ Over Time",
      "description": "Each model's estimated Mathematical Reasoning IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/mathematical-reasoning-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/mathematical-reasoning-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "academic-reasoning-iq-rankings",
      "title": "Academic Reasoning IQ Rankings",
      "description": "Each model's estimated Academic Reasoning IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/academic-reasoning-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/academic-reasoning-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "academic-reasoning-iq-vs-completion-time",
      "title": "Academic Reasoning IQ vs Speed",
      "description": "Each model's estimated Academic Reasoning IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/academic-reasoning-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/academic-reasoning-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "academic-reasoning-iq-over-time",
      "title": "Academic Reasoning IQ Over Time",
      "description": "Each model's estimated Academic Reasoning IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/academic-reasoning-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/academic-reasoning-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "programmatic-reasoning-iq-rankings",
      "title": "Programmatic Reasoning IQ Rankings",
      "description": "Each model's estimated Programmatic Reasoning IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/programmatic-reasoning-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/programmatic-reasoning-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "programmatic-reasoning-iq-vs-completion-time",
      "title": "Programmatic Reasoning IQ vs Speed",
      "description": "Each model's estimated Programmatic Reasoning IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/programmatic-reasoning-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/programmatic-reasoning-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "programmatic-reasoning-iq-over-time",
      "title": "Programmatic Reasoning IQ Over Time",
      "description": "Each model's estimated Programmatic Reasoning IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/programmatic-reasoning-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/programmatic-reasoning-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "computer-use-iq-rankings",
      "title": "Computer Use IQ Rankings",
      "description": "Each model's estimated Computer Use IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/computer-use-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/computer-use-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "computer-use-iq-vs-completion-time",
      "title": "Computer Use IQ vs Speed",
      "description": "Each model's estimated Computer Use IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/computer-use-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/computer-use-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "computer-use-iq-over-time",
      "title": "Computer Use IQ Over Time",
      "description": "Each model's estimated Computer Use IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/computer-use-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/computer-use-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "reliability-iq-rankings",
      "title": "Reliability IQ Rankings",
      "description": "Each model's estimated Reliability IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/reliability-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/reliability-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "reliability-iq-vs-completion-time",
      "title": "Reliability IQ vs Speed",
      "description": "Each model's estimated Reliability IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/reliability-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/reliability-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "reliability-iq-over-time",
      "title": "Reliability IQ Over Time",
      "description": "Each model's estimated Reliability IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/reliability-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/reliability-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "knowledge-work-iq-rankings",
      "title": "Knowledge Work IQ Rankings",
      "description": "Each model's estimated Knowledge Work IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/knowledge-work-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/knowledge-work-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "benchmarkBar"
      ]
    },
    {
      "id": "knowledge-work-iq-vs-completion-time",
      "title": "Knowledge Work IQ vs Speed",
      "description": "Each model's estimated Knowledge Work IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/knowledge-work-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/knowledge-work-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "responseLines"
      ]
    },
    {
      "id": "knowledge-work-iq-over-time",
      "title": "Knowledge Work IQ Over Time",
      "description": "Each model's estimated Knowledge Work IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/knowledge-work-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/knowledge-work-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "timeline"
      ]
    },
    {
      "id": "engineering-design-iq",
      "title": "Engineering Design IQ Bell Curve",
      "description": "Each model's Engineering Design IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/engineering-design-iq/",
      "image": "https://www.aiiq.org/og/charts/engineering-design-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "engineering-design-iq-vs-effective-cost",
      "title": "Engineering Design IQ vs Cost",
      "description": "Each model's Engineering Design IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/engineering-design-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/engineering-design-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "engineering-design-iq-rankings",
      "title": "Engineering Design IQ Rankings",
      "description": "Each model's estimated Engineering Design IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/engineering-design-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/engineering-design-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "engineering-design-iq-vs-completion-time",
      "title": "Engineering Design IQ vs Speed",
      "description": "Each model's estimated Engineering Design IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/engineering-design-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/engineering-design-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "engineering-design-iq-over-time",
      "title": "Engineering Design IQ Over Time",
      "description": "Each model's estimated Engineering Design IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/engineering-design-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/engineering-design-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "cybersecurity-iq",
      "title": "Cybersecurity IQ Bell Curve",
      "description": "Each model's Cybersecurity IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/cybersecurity-iq/",
      "image": "https://www.aiiq.org/og/charts/cybersecurity-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "cybersecurity-iq-vs-effective-cost",
      "title": "Cybersecurity IQ vs Cost",
      "description": "Each model's Cybersecurity IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/cybersecurity-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/cybersecurity-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "cybersecurity-iq-rankings",
      "title": "Cybersecurity IQ Rankings",
      "description": "Each model's estimated Cybersecurity IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/cybersecurity-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/cybersecurity-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "cybersecurity-iq-vs-completion-time",
      "title": "Cybersecurity IQ vs Speed",
      "description": "Each model's estimated Cybersecurity IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/cybersecurity-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/cybersecurity-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "cybersecurity-iq-over-time",
      "title": "Cybersecurity IQ Over Time",
      "description": "Each model's estimated Cybersecurity IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/cybersecurity-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/cybersecurity-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "bio-iq",
      "title": "Biology IQ Bell Curve",
      "description": "Each model's Biology IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/bio-iq/",
      "image": "https://www.aiiq.org/og/charts/bio-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "bio-iq-vs-effective-cost",
      "title": "Biology IQ vs Cost",
      "description": "Each model's Biology IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/bio-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/bio-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "bio-iq-rankings",
      "title": "Biology IQ Rankings",
      "description": "Each model's estimated Biology IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/bio-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/bio-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "bio-iq-vs-completion-time",
      "title": "Biology IQ vs Speed",
      "description": "Each model's estimated Biology IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/bio-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/bio-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "bio-iq-over-time",
      "title": "Biology IQ Over Time",
      "description": "Each model's estimated Biology IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/bio-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/bio-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "machine-learning-iq",
      "title": "AI/ML Engineering IQ Bell Curve",
      "description": "Each model's AI/ML Engineering IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/machine-learning-iq/",
      "image": "https://www.aiiq.org/og/charts/machine-learning-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "machine-learning-iq-vs-effective-cost",
      "title": "AI/ML Engineering IQ vs Cost",
      "description": "Each model's AI/ML Engineering IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/machine-learning-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/machine-learning-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "machine-learning-iq-rankings",
      "title": "AI/ML Engineering IQ Rankings",
      "description": "Each model's estimated AI/ML Engineering IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/machine-learning-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/machine-learning-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "machine-learning-iq-vs-completion-time",
      "title": "AI/ML Engineering IQ vs Speed",
      "description": "Each model's estimated AI/ML Engineering IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/machine-learning-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/machine-learning-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "machine-learning-iq-over-time",
      "title": "AI/ML Engineering IQ Over Time",
      "description": "Each model's estimated AI/ML Engineering IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/machine-learning-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/machine-learning-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "finance-iq",
      "title": "Finance IQ Bell Curve",
      "description": "Each model's Finance IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/finance-iq/",
      "image": "https://www.aiiq.org/og/charts/finance-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "finance-iq-vs-effective-cost",
      "title": "Finance IQ vs Cost",
      "description": "Each model's Finance IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/finance-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/finance-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "finance-iq-rankings",
      "title": "Finance IQ Rankings",
      "description": "Each model's estimated Finance IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/finance-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/finance-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "finance-iq-vs-completion-time",
      "title": "Finance IQ vs Speed",
      "description": "Each model's estimated Finance IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/finance-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/finance-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "finance-iq-over-time",
      "title": "Finance IQ Over Time",
      "description": "Each model's estimated Finance IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/finance-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/finance-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "writing-iq",
      "title": "Writing IQ Bell Curve",
      "description": "Each model's Writing IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/writing-iq/",
      "image": "https://www.aiiq.org/og/charts/writing-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "writing-iq-vs-effective-cost",
      "title": "Writing IQ vs Cost",
      "description": "Each model's Writing IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/writing-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/writing-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "writing-iq-rankings",
      "title": "Writing IQ Rankings",
      "description": "Each model's estimated Writing IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/writing-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/writing-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "writing-iq-vs-completion-time",
      "title": "Writing IQ vs Speed",
      "description": "Each model's estimated Writing IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/writing-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/writing-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "writing-iq-over-time",
      "title": "Writing IQ Over Time",
      "description": "Each model's estimated Writing IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/writing-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/writing-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "software-engineering-iq",
      "title": "Software Engineering IQ Bell Curve",
      "description": "Each model's Software Engineering IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/software-engineering-iq/",
      "image": "https://www.aiiq.org/og/charts/software-engineering-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "software-engineering-iq-vs-effective-cost",
      "title": "Software Engineering IQ vs Cost",
      "description": "Each model's Software Engineering IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/software-engineering-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/software-engineering-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "software-engineering-iq-rankings",
      "title": "Software Engineering IQ Rankings",
      "description": "Each model's estimated Software Engineering IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/software-engineering-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/software-engineering-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "software-engineering-iq-vs-completion-time",
      "title": "Software Engineering IQ vs Speed",
      "description": "Each model's estimated Software Engineering IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/software-engineering-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/software-engineering-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "software-engineering-iq-over-time",
      "title": "Software Engineering IQ Over Time",
      "description": "Each model's estimated Software Engineering IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/software-engineering-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/software-engineering-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "webdev-design-iq",
      "title": "WebDev & Design IQ Bell Curve",
      "description": "Each model's WebDev & Design IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/webdev-design-iq/",
      "image": "https://www.aiiq.org/og/charts/webdev-design-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "webdev-design-iq-vs-effective-cost",
      "title": "WebDev & Design IQ vs Cost",
      "description": "Each model's WebDev & Design IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/webdev-design-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/webdev-design-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "webdev-design-iq-rankings",
      "title": "WebDev & Design IQ Rankings",
      "description": "Each model's estimated WebDev & Design IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/webdev-design-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/webdev-design-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "webdev-design-iq-vs-completion-time",
      "title": "WebDev & Design IQ vs Speed",
      "description": "Each model's estimated WebDev & Design IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/webdev-design-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/webdev-design-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "webdev-design-iq-over-time",
      "title": "WebDev & Design IQ Over Time",
      "description": "Each model's estimated WebDev & Design IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/webdev-design-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/webdev-design-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "emotional-reasoning-iq-rankings",
      "title": "Emotional Reasoning IQ Rankings",
      "description": "Each model's estimated Emotional Reasoning IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/emotional-reasoning-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/emotional-reasoning-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "emotional-reasoning-iq-vs-completion-time",
      "title": "Emotional Reasoning IQ vs Speed",
      "description": "Each model's estimated Emotional Reasoning IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/emotional-reasoning-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/emotional-reasoning-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "emotional-reasoning-iq-over-time",
      "title": "Emotional Reasoning IQ Over Time",
      "description": "Each model's estimated Emotional Reasoning IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/emotional-reasoning-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/emotional-reasoning-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "legal-iq",
      "title": "Legal IQ Bell Curve",
      "description": "Each model's Legal IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/legal-iq/",
      "image": "https://www.aiiq.org/og/charts/legal-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "legal-iq-vs-effective-cost",
      "title": "Legal IQ vs Cost",
      "description": "Each model's Legal IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/legal-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/legal-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "legal-iq-rankings",
      "title": "Legal IQ Rankings",
      "description": "Each model's estimated Legal IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/legal-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/legal-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "legal-iq-vs-completion-time",
      "title": "Legal IQ vs Speed",
      "description": "Each model's estimated Legal IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/legal-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/legal-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "legal-iq-over-time",
      "title": "Legal IQ Over Time",
      "description": "Each model's estimated Legal IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/legal-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/legal-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    },
    {
      "id": "healthcare-iq",
      "title": "Healthcare IQ Bell Curve",
      "description": "Each model's Healthcare IQ, placed on a standard normal IQ distribution. Domain composites are provisional and sit outside Composite IQ.",
      "url": "https://www.aiiq.org/charts/healthcare-iq/",
      "image": "https://www.aiiq.org/og/charts/healthcare-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "bellCurve"
      ]
    },
    {
      "id": "healthcare-iq-vs-effective-cost",
      "title": "Healthcare IQ vs Cost",
      "description": "Each model's Healthcare IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).",
      "url": "https://www.aiiq.org/charts/healthcare-iq-vs-effective-cost/",
      "image": "https://www.aiiq.org/og/charts/healthcare-iq-vs-effective-cost.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "color"
      ]
    },
    {
      "id": "healthcare-iq-rankings",
      "title": "Healthcare IQ Rankings",
      "description": "Each model's estimated Healthcare IQ, ranked highest to lowest. Defaults to current-generation models.",
      "url": "https://www.aiiq.org/charts/healthcare-iq-rankings/",
      "image": "https://www.aiiq.org/og/charts/healthcare-iq-rankings.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "benchmarkBar"
      ]
    },
    {
      "id": "healthcare-iq-vs-completion-time",
      "title": "Healthcare IQ vs Speed",
      "description": "Each model's estimated Healthcare IQ against its completion time, which is time to last token (TTLT). Drag the input and output sliders to see how it changes with the workload.",
      "url": "https://www.aiiq.org/charts/healthcare-iq-vs-completion-time/",
      "image": "https://www.aiiq.org/og/charts/healthcare-iq-vs-completion-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "responseLines"
      ]
    },
    {
      "id": "healthcare-iq-over-time",
      "title": "Healthcare IQ Over Time",
      "description": "Each model's estimated Healthcare IQ by release date. Step-lines connect each provider's flagship models over time.",
      "url": "https://www.aiiq.org/charts/healthcare-iq-over-time/",
      "image": "https://www.aiiq.org/og/charts/healthcare-iq-over-time.png",
      "relatedBenchmarks": [],
      "tags": [
        "Applied Domains",
        "timeline"
      ]
    }
  ]
}