Mathematics · Benchmark profile
An independently evaluated MATH-500 result from Artificial Analysis.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on Artificial Analysis MATH-500
GPT-5 (high) leads at 99.4%, followed by o3 (99.2%) and GPT-5 (medium) (99.1%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
3 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5 (high) | #1 | OpenAI | 99.4% |
| o3 | #2 | OpenAI | 99.2% |
| GPT-5 (medium) | #3 | OpenAI | 99.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | GPT-5 (high) gpt-5-high | OpenAI | closed | Estimated reference | 99.4% |
| #2 | o3 o3 | OpenAI | closed | Reference only | 99.2% |
| #3 | GPT-5 (medium) gpt-5-medium | OpenAI | closed | Reference only | 99.1% |
The top of this snapshot is led by GPT-5 (high) at 99.4%; third place is 0.30 points behind. The top-3 spread is 0.30 points.
About Artificial Analysis MATH-500
An independently evaluated MATH-500 result from Artificial Analysis. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
An independently evaluated MATH-500 result from Artificial Analysis.
GPT-5 (high) by OpenAI currently leads with 99.4%.
3 models in the LuminaBench cohort have a qualifying score on this benchmark.
Related
