SuperCLUE General (2025 Annual) - Science Reasoning: leaderboard
SuperCLUE general leaderboard, 2025 Annual edition (2025年度测评): science reasoning (科学推理) score from the 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. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (High) | 78.63 | #67 (Claude Opus 4.6) |
| 2 | Gemini 3.1 Pro (Preview) (High) | 77.05 | #64 (Gemini 3.1 Pro (Preview)) |
| 3 | GPT-5.2 (High) | 75.21 | #115 (GPT-5.2) |
| 4 | Doubao-Seed-2.0-Pro-260215 | 75.21 | #86 |
| 5 | Qwen 3.5 122B A10B (Thinking) | 74.59 | #184 (Qwen 3.5 122B A10B) |
| 6 | Gemini 3 Flash (Preview) | 74.17 | #90 |
| 7 | Gemini 3 Pro (Preview) | 73.77 | #71 |
| 8 | Claude Opus 4.5 (Thinking) | 73.77 | #87 (Claude Opus 4.5) |
| 9 | Qwen 3.5 397B A17B (Thinking) | 73.77 | #154 (Qwen 3.5 397B A17B) |
| 10 | Qwen 3.5 27B (Thinking) | 72.13 | #192 (Qwen 3.5 27B) |
| 11 | DeepSeek V3.2 (Thinking) | 71.31 | #210 (DeepSeek V3.2) |
| 12 | Qwen 3 Max (Thinking) | 68.85 | #213 (Qwen 3 Max) |
| 13 | Grok 4 | 68.03 | #189 |
| 14 | GLM-5 | 67.21 | #149 |
| 15 | Kimi K2.5 (Thinking) | 67.21 | #152 (Kimi K2.5) |
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-2025-annual-science-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.