MathArena Apex — leaderboard
MathArena Apex is a challenging math contest benchmark featuring the most difficult mathematical problems designed to test advanced reasoning and problem-solving abilities of AI models. It focuses on olympiad-level mathematics and complex multi-step mathematical reasoning.
Metric: Score (self-reported). Source: matharena.ai. Status: saturation imminent. 47 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 OpenAI | 80.21 |
| 2 | GPT-5.4 Pro OpenAI | 69.79 |
| 3 | Gemini 3.1 Pro Preview Google | 60.94 |
| 4 | GPT-5.4 OpenAI | 54.17 |
| 5 | Qwen3.7 Max max | 44.5 |
| 6 | Claude Opus 4.7 Anthropic | 40.62 |
| 7 | Nex-N2-Pro | 36.5 |
| 8 | Claude Opus 4.6 max | 34.5 |
| 9 | Anthropic Opus 4.6 (Max) Anthropic | 34.45 |
| 10 | Gemini 3.5 Flash Google | 32.29 |
Interactive version: theaggregate.ai/benchmark?slug=matharena-apex · How the rankings work · Data refreshed daily, snapshot 2026-07-22.