SuperCLUE General (November 2025) - Math Reasoning: leaderboard
SuperCLUE general leaderboard, November 2025 edition (2025年11月): math reasoning (数学推理) score (总排行榜 sheet). SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around February 2027. 32 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V3.2 Speciale | 75.24 | #138 |
| 2 | GPT-5.1 (High) | 74.07 | #145 (GPT-5.1) |
| 3 | DeepSeek V3.2 (Thinking) | 69.44 | #210 (DeepSeek V3.2) |
| 4 | Gemini 3 Pro (Preview) | 67.59 | #71 |
| 5 | O3 (High) | 66.67 | #132 (O3) |
| 6 | GPT-5.2 (High) | 64.49 | #115 (GPT-5.2) |
| 7 | Kimi K2 (Thinking) | 63.89 | #252 (Kimi K2) |
| 8 | GPT-OSS-120B | 60.65 | #346 |
| 9 | Gemini 2.5 Pro | 60.19 | #159 |
| 10 | GLM-4.7 | 60 | #202 |
| 11 | GLM-4.6 | 58.33 | #265 |
| 12 | Claude Opus 4.5 (Thinking) | 58.33 | #87 (Claude Opus 4.5) |
| 13 | Grok 4.1 Fast (Reasoning) | 56.48 | #227 (Grok 4.1 Fast) |
| 14 | Qwen 3 Max | 55.56 | #213 |
| 15 | Qwen 3 Max (Preview) (Thinking) | 55.56 | #248 (Qwen 3 Max (Preview)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-november-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.