FrontierMath
An advanced mathematics benchmark curated around difficult research-style math problems.
Math Ranking
Signals for advanced mathematics, contest-style math, and visual math reasoning.
Main rankings require at least 2 of 2 included sourced benchmark rows.
Within the main ranking, rows are sorted by average normalized score; coverage is shown separately and used only as a tie-breaker.
Missing benchmark data is not treated as zero; models below the threshold appear under limited evidence.
| Rank | Model | Provider | Score | Coverage | Source | Source Type | Verified | Last Updated |
|---|
Limited Evidence
| Model | Provider | Score | Coverage | Freshest Source | Last Updated |
|---|---|---|---|---|---|
| OpenAI GPT-5.4 | OpenAI | 47.6 | 1/2 | Introducing GPT-5.4 Accessed 2026-06-11 | 2026-06-11 |
| OpenAI GPT-5.2 Thinking | OpenAI | 40.3 | 1/2 | Introducing GPT-5.2 Accessed 2026-06-11 | 2026-06-11 |
MathVista
A visual math reasoning benchmark for multimodal models.