Benchmark Correlation Heatmap
A pairwise matrix of source-backed benchmark score correlations across public models. Color shows Pearson r; each cell uses models with both benchmark scores.
Benchmark Correlation Heatmap
Benchmark Correlation Heatmap
A pairwise matrix of source-backed benchmark score correlations across public models. Color shows Pearson r; each cell uses models with both benchmark scores.
How to read this chart
Each cell compares two benchmark columns across models with both values present. Stronger color indicates a stronger Pearson correlation.
Data sources
ARC PrizeEpoch AI FrontierMathVals.aiArtificial AnalysisMathArenaArena.ai WebDevDesignArena FrontendDesignArena Full StackVals.ai Vibe Code BenchVals.ai Vibe Code Bench v1.1LLM StatsScale LabsScale Labs SWE-Bench Pro Public DatasetDeepSWE v1.1DeepSWESWE MarathonMercor APEX-SWECognition FrontierCodeSWE-rebenchArtificial Analysis Terminal-Bench v2.1Vals.ai Terminal-Bench 2.1OSWorldanthropic-system-cardToolathlonScale LabsAgents' Last ExamBullshitBench v2Kaggle FACTS Grounding leaderboardArena.aiEQ-Bench 3AttuneBench
More / ExperimentalTerminal-Bench 2.0 Benchmark ScoresLegacy Terminal-Bench 2.0 scores retained for historical comparison. Color = provider.Data: Terminal-BenchOpen chartMore / ExperimentalARC-AGI-2 Cost EfficiencyX = ARC Prize reported cost/task (log). Y = ARC-AGI-2 %. Each line connects one model's published reasoning-effort levels, so the score-vs-cost tradeoff is visible per model. Shows each model line's current and previous model. Color = provider.Data: ARC PrizeOpen chartMore / ExperimentalFlagship Lab Benchmark Correlation HeatmapA pairwise benchmark correlation matrix using only the latest flagship model from each major US and Chinese lab.Data: ARC Prize, Epoch AI FrontierMath, Vals.ai +28 moreOpen chartMore / ExperimentalARC-AGI-3 vs CostX = ARC Prize reported Cost (V3) (log). Y = ARC-AGI-3 %. Color = provider.Data: ARC PrizeOpen chartMore / ExperimentalARC-AGI-2 vs Cost/TaskX = ARC Prize reported cost/task (log). Y = ARC-AGI-2 %. Color = provider.Data: ARC PrizeOpen chartMore / ExperimentalARC-AGI-1 vs Cost/TaskX = ARC Prize reported cost/task (log). Y = ARC-AGI-1 %. Color = provider.Data: ARC PrizeOpen chart