SuperCLUE General (September 2025) - Science Reasoning: leaderboard
SuperCLUE general leaderboard, September 2025 edition (2025年9月): science reasoning (科学推理) 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 | Kimi K2 (Thinking) | 54.31 | #252 (Kimi K2) |
| 2 | O4 Mini (High) | 54.31 | #185 (O4 Mini) |
| 3 | Gemini 3 Pro (Preview) | 53.45 | #71 |
| 4 | GPT-5.1 (High) | 53.45 | #145 (GPT-5.1) |
| 5 | Doubao-Seed-1.6-thinking-250715 | 52.59 | #169 |
| 6 | GPT-OSS-120B | 50.86 | #346 |
| 7 | Gemini 2.5 Pro | 50 | #159 |
| 8 | Qwen 3 Max | 48.28 | #213 |
| 9 | DeepSeek V3.1 Terminus (Thinking) | 47.41 | #224 (DeepSeek V3.1 Terminus) |
| 10 | Qwen 3 235B A22B 2507 (Thinking) | 46.55 | #263 |
| 11 | DeepSeek V3.2 Exp (Thinking) | 45.69 | #241 (DeepSeek V3.2 Exp) |
| 12 | Claude Opus 4.1 (Thinking) | 45.69 | #146 (Claude Opus 4.1) |
| 13 | GPT-5 (High) | 44.83 | #105 (GPT-5) |
| 14 | GLM-4.6 | 43.97 | #265 |
| 15 | GLM-4.5 | 43.1 | #283 |
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-science-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.