Arena.ai Overall Benchmark Scores
Human-preference Arena.ai Overall Elo scores. Color = provider.
Arena.ai Overall Benchmark Scores
Arena.ai Overall Benchmark Scores
Human-preference Arena.ai Overall Elo scores. 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
Arena.ai Overall Elo vs Cost
Arena.ai Overall Elo vs Cost
X = effective cost (log). Y = Arena.ai Overall Elo. Color = provider.
Controls:
How to read this chart
Each point is a public model. The chart compares Arena.ai Overall Elo against Effective Cost (per 1M I/O Tokens), with color showing the model provider.
Data sources
CoreAI Models on the IQ Bell CurveEach model's estimated IQ plotted on a standard normal IQ distributionData: ARC Prize, Epoch AI FrontierMath, Vals.ai +25 moreOpen chartEQ / DiagnosticEQ-Bench 3 Benchmark ScoresAI-judged EQ-Bench 3 Elo, a style-sensitive emotional reasoning signal. Color = provider.Data: EQ-Bench 3Open chartEQ / DiagnosticAttuneBench Benchmark ScoresDefault-mode AttuneBench Composite scores from real human-AI conversations. Color = provider.Data: AttuneBenchOpen chartEQ / DiagnosticEmotional Reasoning (EQ)Diagnostic Emotional Reasoning scores, excluded from Composite IQ until the benchmark base is stronger.Data: EQ-Bench 3, Arena.ai, AttuneBenchOpen chartCoreIQ vs EQX = diagnostic EQ. Y = IQ. Color = model provider.Data: Arena.ai, EQ-Bench 3, AttuneBench +28 moreOpen chartCostEQ vs Effective CostDiagnostic EQ plotted against effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).Data: Artificial Analysis, ARC Prize, Vals.ai +3 moreOpen chart