SuperCLUE General (September 2025) - Math Reasoning: leaderboard
SuperCLUE general leaderboard, September 2025 edition (2025年9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: Estimated already saturated. 37 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 (High) | 82.73 | #145 (GPT-5.1) |
| 2 | Kimi K2 (Thinking) | 80.91 | #252 (Kimi K2) |
| 3 | Gemini 3 Pro (Preview) | 79.09 | #71 |
| 4 | O3 (High) | 77.27 | #132 (O3) |
| 5 | GPT-5 (High) | 73.64 | #105 (GPT-5) |
| 6 | O4 Mini (High) | 72.73 | #185 (O4 Mini) |
| 7 | Gemini 2.5 Pro | 71.82 | #159 |
| 8 | GPT-OSS-120B | 70.91 | #346 |
| 9 | Qwen 3 Next 80B A3B (Thinking) | 66.36 | #312 |
| 10 | Gemini 2.5 Flash | 62.73 | #255 |
| 11 | Qwen 3 Max | 62.73 | #213 |
| 12 | Grok 4 Fast (Reasoning) | 62.73 | #266 (Grok 4 Fast) |
| 13 | DeepSeek V3.2 Exp (Thinking) | 60.91 | #241 (DeepSeek V3.2 Exp) |
| 14 | Doubao-Seed-1.6-thinking-250715 | 60.55 | #169 |
| 15 | DeepSeek V3.1 Terminus (Thinking) | 60 | #224 (DeepSeek V3.1 Terminus) |
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-september-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.