Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Mathematics benchmark
Artificial Analysis MATH-500. Every model the catalog carries a published AA MATH-500 value for, ranked by that value.
An independently evaluated MATH-500 result from Artificial Analysis. 11 models in the ModelChoice catalog have a published value.
Each point is a model with a published AA MATH-500 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
11 models with a published AA MATH-500 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Accuracy |
|---|---|---|---|
| 1 | OpenAI | 99.4 | |
| 1 | OpenAI | 99.4 | |
| 3 | OpenAI | 99.2 | |
| 4 |
What the benchmark measures and how its value is published, from the source’s own record.
AA MATH-500 (Artificial Analysis MATH-500) is a mathematics benchmark published by Artificial Analysis MATH-500 Benchmark Leaderboard. An independently evaluated MATH-500 result from Artificial Analysis. Its evaluation set is described by the source as 500 competition mathematics problems. The source rates its difficulty as high school to undergraduate mathematics.
Each model's result is published by Artificial Analysis MATH-500 Benchmark Leaderboard as accuracy. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 11 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| OpenAI |
| 99.1 |
| 5 | xAI | 99.0 |
| 6 | OpenAI | 98.9 |
| 7 | DeepSeek | 98.3 |
| 8 | Anthropic | 98.2 |
| 9 | Moonshot AI | 97.1 |
| 10 | OpenAI | 97.0 |
| 11 | 96.7 |
Evidence key: ObservedLast good
Rows are ordered by the value Artificial Analysis MATH-500 Benchmark Leaderboard published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.