SuperCLUE General (May 2025) - Science Reasoning: leaderboard
Metric: Score. Source: www.superclueai.com. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-thinking-pro-250415 | 52.08 |
| 2 | O4 Mini (High) | 52 |
| 3 | DeepSeek R1 | 49.5 |
| 4 | ERNIE-X1-Turbo-32K | 48.98 |
| 5 | Gemini 2.5 Flash (Preview 04-17) | 47.52 |
| 6 | Qwen 3 32B (Thinking) | 47.52 |
| 7 | SenseNova V6 Reasoner | 47.52 |
| 8 | Gemini 2.5 Flash (Preview 05-20) | 46.53 |
| 9 | Claude Opus 4 (Thinking) | 45.54 |
| 10 | Gemini 2.5 Pro (Preview 05-06) | 43.56 |
| 11 | DeepSeek V3 (0324) | 41.58 |
| 12 | DeepSeek R1 Distill Qwen 32B | 38.89 |
| 13 | Llama 4 Maverick Instruct | 38.61 |
| 14 | Kimi K1.5 | 38.61 |
| 15 | O3 | 25.74 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-may-2025-science-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.