Flagship Lab Benchmark Correlation Heatmap
A pairwise benchmark correlation matrix using only the latest flagship model from each major US and Chinese lab.
Flagship Lab Benchmark Correlation Heatmap
Flagship Lab Benchmark Correlation Heatmap
A pairwise benchmark correlation matrix using only the latest flagship model from each major US and Chinese lab.
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 / ExperimentalBenchmark Correlation HeatmapA pairwise matrix of source-backed benchmark score correlations across public models. Color shows Pearson r; each cell uses models with both benchmark scores.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