SuperCLUE General (May 2025) - Math Reasoning: leaderboard
SuperCLUE general leaderboard, May 2025 edition (2025年5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. 40 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | 360Zhinao2-O1.5 | 62.86 | #395 |
| 2 | DeepSeek R1 | 62.1 | #262 |
| 3 | Doubao-1.5-thinking-pro-250415 | 62.1 | #226 |
| 4 | SenseNova V6 Reasoner | 62.1 | #317 |
| 5 | Qwen 3 30B A3B (Thinking) | 61.29 | #496 (Qwen 3 30B A3B) |
| 6 | Qwen 3 8B (Thinking) | 60.48 | #678 (Qwen 3 8B) |
| 7 | DeepSeek R1 Distill Qwen 32B | 60.33 | #662 |
| 8 | Qwen 3 235B A22B (Thinking) | 58.87 | #323 (Qwen 3 235B A22B) |
| 9 | O4 Mini (High) | 57.72 | #185 (O4 Mini) |
| 10 | ERNIE-X1-Turbo-32K | 57.63 | #288 |
| 11 | Gemini 2.5 Flash (Preview 04-17) | 57.26 | #246 |
| 12 | O3 | 56.45 | #132 |
| 13 | Qwen 3 32B (Thinking) | 56.45 | #449 (Qwen 3 32B) |
| 14 | Gemini 2.5 Flash (Preview 05-20) | 56.45 | #229 |
| 15 | DeepSeek V3 (0324) | 55.65 | #349 |
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-may-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.