Maths
MATH-500
500 competition maths problems sampled from the MATH benchmark, graded on the final answer.
MATH-500 is scored as a percentage of questions answered correctly. 3 of the 159 models in this index report a score for it. The highest published figure here is 97.3%, from DeepSeek-R1.
Reported scores
Top 3 on MATH-500
Ordered by the figure each maker published. Models that have not reported this benchmark are not listed — an absent score is not a low score.
| # | Model | Published score |
|---|---|---|
| 1 | DeepSeek-R1DeepSeek | |
| 2 | DeepSeek-R1-Distill-Qwen-32BDeepSeek | |
| 3 | DeepSeek-R1-Distill-Llama-8BDeepSeek |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
How to read this score
MATH-500 is broader and easier than AIME, covering algebra, geometry, number theory and precalculus. It is useful for separating mid-tier models that all score near zero on AIME.
Where it is weak
The frontier has saturated it — several models sit above 97%, where the remaining difference is mostly grading noise rather than capability.