{
  "apiVersion": "1",
  "methodologyVersion": "2026-07-09-gso-ml-domain",
  "updatedAt": "2026-07-13T21:57:32.936Z",
  "charts": [
    {
      "id": "iq-bell-curve",
      "title": "AI Models on the IQ Bell Curve",
      "description": "Each model's estimated IQ plotted 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": "frontier-iq-over-time",
      "title": "Frontier IQ Over Time",
      "description": "X = release date. Y = estimated IQ. Provider step-lines connect each provider's flagship frontier checkpoints 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 the company that trained them.",
      "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",
      "description": "Each model's Abstract Reasoning IQ plotted 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",
      "description": "Each model's Mathematical Reasoning IQ plotted 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": "scientific-reasoning-iq",
      "title": "Scientific Reasoning IQ",
      "description": "Each model's Scientific Reasoning IQ plotted on a standard normal IQ distribution",
      "url": "https://www.aiiq.org/charts/scientific-reasoning-iq/",
      "image": "https://www.aiiq.org/og/charts/scientific-reasoning-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "frontend-engineering-iq",
      "title": "Frontend Engineering IQ",
      "description": "Each model's Frontend Engineering IQ plotted on a standard normal IQ distribution",
      "url": "https://www.aiiq.org/charts/frontend-engineering-iq/",
      "image": "https://www.aiiq.org/og/charts/frontend-engineering-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "backend-engineering-iq",
      "title": "Backend Engineering IQ",
      "description": "Each model's Backend Engineering IQ plotted on a standard normal IQ distribution",
      "url": "https://www.aiiq.org/charts/backend-engineering-iq/",
      "image": "https://www.aiiq.org/og/charts/backend-engineering-iq.png",
      "relatedBenchmarks": [],
      "tags": [
        "IQ Dimensions",
        "bellCurve"
      ]
    },
    {
      "id": "computer-use-iq",
      "title": "Computer Use IQ",
      "description": "Each model's Computer Use IQ plotted 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",
      "description": "Each model's Reliability IQ plotted 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": "emotional-reasoning-eq",
      "title": "Emotional Reasoning (EQ)",
      "description": "Diagnostic Emotional Reasoning scores, excluded from Composite IQ until the benchmark base is stronger.",
      "url": "https://www.aiiq.org/charts/emotional-reasoning-eq/",
      "image": "https://www.aiiq.org/og/charts/emotional-reasoning-eq.png",
      "relatedBenchmarks": [],
      "tags": [
        "EQ / Diagnostic",
        "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": "proofbench-scores",
      "title": "ProofBench Benchmark Scores",
      "description": "Each model's ProofBench score. Color = provider.",
      "url": "https://www.aiiq.org/charts/proofbench-scores/",
      "image": "https://www.aiiq.org/og/charts/proofbench-scores.png",
      "relatedBenchmarks": [
        "proofbench"
      ],
      "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 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": "frontierswe-scores",
      "title": "FrontierSWE Scores",
      "description": "FrontierSWE leaderboard tracking for software-engineering skill at the edge of human ability. Color = provider.",
      "url": "https://www.aiiq.org/charts/frontierswe-scores/",
      "image": "https://www.aiiq.org/og/charts/frontierswe-scores.png",
      "relatedBenchmarks": [
        "frontierswe"
      ],
      "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": "deepswe-scores",
      "title": "DeepSWE Benchmark Scores",
      "description": "Each model's DeepSWE Pass@1 score. Color = provider.",
      "url": "https://www.aiiq.org/charts/deepswe-scores/",
      "image": "https://www.aiiq.org/og/charts/deepswe-scores.png",
      "relatedBenchmarks": [
        "deepswe"
      ],
      "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": "swe-bench-verified-scores",
      "title": "SWE-Bench Verified Benchmark Scores",
      "description": "Each model's SWE-Bench Verified score. Color = provider.",
      "url": "https://www.aiiq.org/charts/swe-bench-verified-scores/",
      "image": "https://www.aiiq.org/og/charts/swe-bench-verified-scores.png",
      "relatedBenchmarks": [
        "swebench-verified"
      ],
      "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": "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": "terminal-bench-2-1-scores",
      "title": "Terminal-Bench 2.1 Benchmark Scores",
      "description": "Each model's Terminal-Bench 2.1 pass@1 score, using Artificial Analysis as canonical and Vals.ai as fallback. Color = provider.",
      "url": "https://www.aiiq.org/charts/terminal-bench-2-1-scores/",
      "image": "https://www.aiiq.org/og/charts/terminal-bench-2-1-scores.png",
      "relatedBenchmarks": [
        "terminal-bench-2-1"
      ],
      "tags": [
        "IQ Benchmarks",
        "benchmarkBar"
      ]
    },
    {
      "id": "terminal-bench-hard-scores",
      "title": "Terminal-Bench Hard Benchmark Scores",
      "description": "Each model's Terminal-Bench Hard score. Color = provider.",
      "url": "https://www.aiiq.org/charts/terminal-bench-hard-scores/",
      "image": "https://www.aiiq.org/og/charts/terminal-bench-hard-scores.png",
      "relatedBenchmarks": [
        "terminal-bench-hard"
      ],
      "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": "toolathlon-scores",
      "title": "Toolathlon Benchmark Scores",
      "description": "Each model's Toolathlon score. Color = provider.",
      "url": "https://www.aiiq.org/charts/toolathlon-scores/",
      "image": "https://www.aiiq.org/og/charts/toolathlon-scores.png",
      "relatedBenchmarks": [
        "toolathlon"
      ],
      "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": "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": "aa-lcr-scores",
      "title": "AA Long Chain Reasoning Scores",
      "description": "Artificial Analysis Long Chain Reasoning scores for long-document extraction, synthesis, and reasoning. Color = provider.",
      "url": "https://www.aiiq.org/charts/aa-lcr-scores/",
      "image": "https://www.aiiq.org/og/charts/aa-lcr-scores.png",
      "relatedBenchmarks": [
        "aa-lcr"
      ],
      "tags": [
        "IQ 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": [
        "EQ / Diagnostic",
        "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": [
        "EQ / Diagnostic",
        "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": [
        "EQ / Diagnostic",
        "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 Effective Cost",
      "description": "Each model's estimated IQ plotted against 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": "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 (Tokens Per Second)",
      "description": "Each model's estimated IQ plotted against its median output speed in tokens per second",
      "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 (Time to First Token)",
      "description": "Each model's estimated IQ plotted against its time to first token (TTFT). Drag the input-length slider from 1K to 10K tokens — dots glide between AA's two measured anchors (values in between are linearly interpolated).",
      "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 End-to-End Response Time",
      "description": "Each model's IQ against its end-to-end response time, built from its own components: time to first answer token (which grows with input length) plus output tokens ÷ tokens-per-second. Drag the input slider (1K–10K tokens) and output slider (100–10K tokens) to see how total latency scales.",
      "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 Speed vs Cost in 3D",
      "description": "3D scatter: X = response time (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 Speed over IQ vs Cost",
      "description": "X = Effective Cost/1M I/O Tokens (log). Y = IQ. Spin rate = speed.",
      "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 Speed",
      "description": "X = response time (log, reversed). Y = IQ. Effective Cost/1M I/O Tokens 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"
      ]
    }
  ]
}