MathArena - HMMT Feb 2026 — leaderboard
Metric: Accuracy (%). Source: matharena.ai. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | GPT-5.5 (xHigh) | 98.48 |
| 3 | GPT-5.4 (xHigh) | 97.73 |
| 4 | GPT-5.2 (High) | 96.97 |
| 5 | Claude Opus 4.6 (High) | 96.21 |
| 6 | Gemini 3.5 Flash | 95.45 |
| 7 | Claude Opus 4.8 (Max) | 95.45 |
| 8 | Gemini 3.1 Pro (Preview) | 94.7 |
| 9 | Kimi K2.6 (Thinking) | 94.7 |
| 10 | DeepSeek V4 Pro (Max) | 93.94 |
| 11 | DeepSeek V4 Flash (Max) | 93.94 |
| 12 | Claude Opus 4.7 (xHigh) | 93.94 |
| 13 | GLM-5.2 | 92.42 |
| 14 | GLM-5.1 | 89.39 |
| 15 | Gemini 3 Flash | 89.39 |
Interactive version: theaggregate.ai/benchmark?slug=matharena-hmmt-feb-2026 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.