SuperCLUE General (November 2025) - Math Reasoning: leaderboard
Metric: Score. Source: www.superclueai.com. 32 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 Speciale | 75.24 |
| 2 | GPT-5.1 (High) | 74.07 |
| 3 | DeepSeek V3.2 (Thinking) | 69.44 |
| 4 | Gemini 3 Pro (Preview) | 67.59 |
| 5 | O3 (High) | 66.67 |
| 6 | GPT-5.2 (High) | 64.49 |
| 7 | Kimi K2 (Thinking) | 63.89 |
| 8 | GPT-OSS-120B | 60.65 |
| 9 | Gemini 2.5 Pro | 60.19 |
| 10 | GLM-4.7 | 60 |
| 11 | GLM-4.6 | 58.33 |
| 12 | Claude Opus 4.5 (Thinking) | 58.33 |
| 13 | Grok 4.1 Fast (Reasoning) | 56.48 |
| 14 | Qwen 3 Max | 55.56 |
| 15 | Qwen 3 Max (Preview) (Thinking) | 55.56 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-november-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.