AI IQ
Subscribe

Mathematical Reasoning

A bird's-eye view of the dimension: the main IQ chart, the effective-cost frontier, and the benchmark charts that feed it.

Mathematical Reasoning IQ Bell Curve
Mathematical Reasoning IQ Bell Curve
Each model's estimated Mathematical Reasoning IQ, placed on a standard normal IQ distribution.

How to read this chart

Models are placed on a standard IQ-style distribution using Mathematical Reasoning IQ. Higher scores appear farther to the right.

Benchmarks in this dimension

FrontierMath Tier 1-3FrontierMath Tier 4AIMEMathArenaProofBench 1.1
Mathematical Reasoning IQ vs Cost
Mathematical Reasoning IQ vs Cost
Each model's estimated Mathematical Reasoning IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).
Controls:
Math1:1Cost

How to read this chart

Each point is a public model. The chart compares Mathematical Reasoning IQ against Effective Cost (per 1M I/O Tokens), with color showing the model provider.

Data sources
Artificial AnalysisARC PrizeVals Index v2 Cost per TestVals.aiEpoch AI FrontierMathProofBench 1.1MathArena
Benchmarks In This Dimension
FrontierMath Tier 1-3 Benchmark Scores
Each model's FrontierMath Tier 1-3 score. Color = provider.

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
Epoch AI FrontierMath
Data updated Oct 10, 2026
FrontierMath Tier 4 Benchmark Scores
Each model's FrontierMath Tier 4 score. Color = provider.

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
Epoch AI FrontierMath
Data updated Oct 10, 2026
AIME Benchmark Scores
Each model's AIME score. Color = provider.

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
Vals.aiArtificial Analysis
Data updated Sep 7, 2026
MathArena Benchmark Scores
Each model's MathArena expected performance. Color = provider.

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
MathArena
Data updated Sep 30, 2026
ProofBench 1.1 Scores
Native Lean 4.25.2 verification including native_decide. Version 1.1 only; not comparable to the unversioned historical cohort. Contributes to Mathematical Reasoning using a provisional calibrated scale.

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
ProofBench 1.1
Data updated Oct 13, 2026