MATH-500 Problem Set

A curated subset of 500 problems from the MATH dataset, covering algebra, counting and probability, geometry, intermediate algebra, number theory, prealgebra, and precalculus.

ModelsModels with a result.27
Top resultBest result on this benchmark.98.8%Ternary Bonsai 2 27B
Top-3 spreadPoints from first to third.0.2 pts
YearYear of release.2021

Result and price

9 of 27 results

Results

27 results
#ModelResultThe score from the source.
04QwQ-32B98.0%
06o4-mini97.5%
07Kimi K297.4%
19MiniCPM5-1BAbove fitFar above this model's index.91.6%
22o1-mini90.0%
24Qwen3 32B88.6%