Benchmarks

Every source-backed benchmark, grouped by cognitive dimension — open any chart for its detail and cost view

Abstract Reasoning

IQ BenchmarksARC-AGI-2 ScoresEach model's ARC-AGI-2 score. Color = provider.Data: ARC PrizeOpen chart IQ BenchmarksARC-AGI-1 Benchmark ScoresEach model's ARC-AGI-1 score. Color = provider.Data: ARC PrizeOpen chart IQ BenchmarksARC-AGI-3 Benchmark ScoresEach model's ARC-AGI-3 score. Color = provider.Data: ARC PrizeOpen chart

Mathematical Reasoning

IQ BenchmarksAIME Benchmark ScoresEach model's AIME score. Color = provider.Data: Vals.ai, Artificial AnalysisOpen chart IQ BenchmarksFrontierMath Tier 1-3 Benchmark ScoresEach model's FrontierMath Tier 1-3 score. Color = provider.Data: Epoch AI FrontierMathOpen chart IQ BenchmarksFrontierMath Tier 4 Benchmark ScoresEach model's FrontierMath Tier 4 score. Color = provider.Data: Epoch AI FrontierMathOpen chart IQ BenchmarksMathArena Benchmark ScoresEach model's MathArena expected performance. Color = provider.Data: MathArenaOpen chart IQ BenchmarksProofBench Benchmark ScoresEach model's ProofBench score. Color = provider.Data: Vals.aiOpen chart

Scientific Reasoning

IQ BenchmarksHumanity's Last Exam Benchmark ScoresEach model's Humanity's Last Exam score. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksGPQA Diamond Benchmark ScoresEach model's GPQA Diamond score. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksSciCode Benchmark ScoresEach model's SciCode score. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksCritPt Benchmark ScoresEach model's CritPt percentage score. Color = provider.Data: Artificial AnalysisOpen chart

Frontend Engineering

IQ BenchmarksArena.ai WebDev ScoresArena.ai WebDev Elo scores for front-end web development. Color = provider.Data: Arena.ai WebDevOpen chart IQ BenchmarksVibe Code Bench ScoresVals.ai Vibe Code Bench v1.1 accuracy for building web applications from scratch. Color = provider.Data: Vals.ai Vibe Code Bench, Vals.ai Vibe Code Bench v1.1Open chart IQ BenchmarksDesignArena Full Stack ScoresDesignArena Full Stack Elo for end-to-end frontend + backend builds. Color = provider.Data: DesignArena Full StackOpen chart IQ BenchmarksDesignArena Frontend ScoresDesignArena Frontend Elo for agentic front-end web apps. Color = provider.Data: DesignArena FrontendOpen chart

Backend Engineering

IQ BenchmarksSWE-Bench Verified Benchmark ScoresEach model's SWE-Bench Verified score. Color = provider.Data: Vals.ai, LLM StatsOpen chart IQ BenchmarksLiveCodeBench Benchmark ScoresEach model's LiveCodeBench score. Color = provider.Data: Vals.aiOpen chart IQ BenchmarksSWE-Bench Pro Benchmark ScoresEach model's SWE-Bench Pro percentage score. Color = provider.Data: Scale Labs, Scale Labs SWE-Bench Pro Public DatasetOpen chart IQ BenchmarksAPEX-SWE ScoresMercor APEX-SWE overall Pass@1 scores for economically valuable software-engineering work. Color = provider.Data: Mercor APEX-SWEOpen chart IQ BenchmarksDeepSWE Benchmark ScoresEach model's DeepSWE Pass@1 score. Color = provider.Data: DeepSWEOpen chart IQ BenchmarksFrontierSWE ScoresFrontierSWE leaderboard tracking for software-engineering skill at the edge of human ability. Color = provider.Data: FrontierSWEOpen chart IQ BenchmarksDeepSWE v1.1 Benchmark ScoresEach model's DeepSWE v1.1 Pass@1 score. Color = provider.Data: DeepSWE v1.1Open chart IQ BenchmarksSWE-rebench Benchmark ScoresEach model's SWE-rebench resolved rate. Color = provider.Data: SWE-rebenchOpen chart IQ BenchmarksFrontierCode Diamond ScoresEach model's FrontierCode Diamond score for high-quality production-code tasks. Color = provider.Data: Cognition FrontierCodeOpen chart IQ BenchmarksSWE Marathon ScoresEach model's SWE Marathon aggregate Resolution Rate (Pass@1). Color = provider.Data: SWE MarathonOpen chart

Computer Use

IQ BenchmarksTerminal-Bench Hard Benchmark ScoresEach model's Terminal-Bench Hard score. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksTerminal-Bench 2.1 Benchmark ScoresEach model's Terminal-Bench 2.1 pass@1 score, using Artificial Analysis as canonical and Vals.ai as fallback. Color = provider.Data: Artificial Analysis Terminal-Bench v2.1, Vals.ai Terminal-Bench 2.1Open chart IQ BenchmarksBrowseComp Benchmark ScoresEach model's BrowseComp score. Color = provider.Data: LLM StatsOpen chart IQ BenchmarksMCP Atlas Benchmark ScoresReal-world MCP tool-use pass rates. Color = provider.Data: Scale Labs, Scale Labs MCP AtlasOpen chart IQ BenchmarksToolathlon Benchmark ScoresEach model's Toolathlon score. Color = provider.Data: LLM Stats, Toolathlon, LLM Stats ToolathlonOpen chart IQ BenchmarksAgents' Last Exam Benchmark ScoresFull / Overall pass rates from Agents' Last Exam. Color = provider.Data: Agents' Last ExamOpen chart IQ BenchmarksOSWorld-Verified Benchmark ScoresEach model's OSWorld-Verified score. Color = provider.Data: LLM Stats, OSWorld, LLM Stats OSWorld-VerifiedOpen chart

Reliability

IQ BenchmarksAA Long Chain Reasoning ScoresArtificial Analysis Long Chain Reasoning scores for long-document extraction, synthesis, and reasoning. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksAA Omniscience ScoresArtificial Analysis Omniscience scores for factual reliability. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksIFBench Benchmark ScoresInstruction-following and constraint-adherence scores. Color = provider.Data: Artificial AnalysisOpen chart IQ BenchmarksBullshitBench v2 ScoresClear Pushback rate: share of attempts where a model clearly challenges a false premise instead of accepting nonsense. Color = provider.Data: BullshitBench v2Open chart IQ BenchmarksFACTS Grounding ScoresGoogle FACTS Grounding scores for long-form responses fully grounded in provided documents. Color = provider.Data: Kaggle FACTS Grounding leaderboardOpen chart

Emotional Reasoning (EQ)

EQ / DiagnosticArena.ai Overall Benchmark ScoresHuman-preference Arena.ai Overall Elo scores. Color = provider.Data: Arena.aiOpen chart EQ / DiagnosticEQ-Bench 3 Benchmark ScoresAI-judged EQ-Bench 3 Elo, a style-sensitive emotional reasoning signal. Color = provider.Data: EQ-Bench 3Open chart EQ / DiagnosticAttuneBench Benchmark ScoresDefault-mode AttuneBench Composite scores from real human-AI conversations. Color = provider.Data: AttuneBenchOpen chart