MathArena - HMMT Nov 2025 — leaderboard
Metric: Accuracy (%). Source: matharena.ai. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | GPT-5.2 (xHigh) | 99.17 |
| 3 | GPT-5.2 (High) | 95.83 |
| 4 | GLM-5 | 94.17 |
| 5 | Step 3.5 Flash | 94.17 |
| 6 | Gemini 3 Pro (Preview) | 93.33 |
| 7 | Grok 4.1 Fast (Reasoning) | 93.33 |
| 8 | Gemini 3 Flash | 93.33 |
| 9 | DeepSeek V3.2 Speciale | 93.33 |
| 10 | GLM-4.6 | 91.67 |
| 11 | GPT-5.1 (High) | 91.67 |
| 12 | Grok 4 Fast (Reasoning) | 90.83 |
| 13 | GPT-OSS-120B (High) | 90 |
| 14 | DeepSeek V3.2 (Thinking) | 90 |
| 15 | GPT-5 (High) | 89.17 |
Interactive version: theaggregate.ai/benchmark?slug=matharena-hmmt-nov-2025 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.