ARC-AGI-3 Benchmark Scores
Each model's ARC-AGI-3 score. Color = provider.
ARC-AGI-3 Benchmark Scores
ARC-AGI-3 Benchmark Scores
Each model's ARC-AGI-3 score. Color = provider.
Controls:
How to read this chart
Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.
Data sources
ARC-AGI-3 vs Cost
ARC-AGI-3 vs Cost
X = ARC Prize reported Cost (V3) (log). Y = ARC-AGI-3 %. Shows all public model generations by default. Color = provider.
Controls:
How to read this chart
Each point is a public model. The chart compares ARC-AGI-3 % against Cost (V3), with color showing the model provider.
Data sources
IQ DimensionsAbstract Reasoning IQEach model's Abstract Reasoning IQ plotted on a standard normal IQ distributionData: ARC PrizeOpen chartCoreAI Models on the IQ Bell CurveEach model's estimated IQ plotted on a standard normal IQ distributionData: ARC Prize, Epoch AI FrontierMath, Vals.ai +27 moreOpen chartIQ BenchmarksARC-AGI-2 ScoresEach model's ARC-AGI-2 score. Color = provider.Data: ARC PrizeOpen chartIQ BenchmarksARC-AGI-1 Benchmark ScoresEach model's ARC-AGI-1 score. Color = provider.Data: ARC PrizeOpen chartMore / ExperimentalARC-AGI-3 Cost EfficiencyX = ARC Prize reported Cost (V3) (log). Y = ARC-AGI-3 %. Each line connects one model's published reasoning-effort levels, so the score-vs-cost tradeoff is visible per model. Defaults to the current model generation. Color = provider.Data: ARC PrizeOpen chartIQ BenchmarksFrontierMath Tier 4 Benchmark ScoresEach model's FrontierMath Tier 4 score. Color = provider.Data: Epoch AI FrontierMathOpen chart