SuperCLUE General (March 2025) - Math Reasoning: leaderboard
SuperCLUE general leaderboard, March 2025 edition (2025年3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. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 Mini (High) | 94.74 | #282 (O3 Mini) |
| 2 | QwQ-32B | 88.6 | #422 |
| 3 | DeepSeek R1 | 85.96 | #262 |
| 4 | DeepSeek R1 Distill Qwen 32B | 85.85 | #662 |
| 5 | Gemini 2.0 Flash (01-21) (Thinking) | 83.33 | #333 (Gemini 2.0 Flash (01-21)) |
| 6 | DeepSeek R1 Distill Qwen 14B | 79.46 | #860 |
| 7 | Claude 3.7 Sonnet | 78.07 | #259 |
| 8 | DeepSeek-R1-Distill-Qwen-7B | 77.23 | #1401 |
| 9 | GLM-Zero-Preview | 74.56 | #682 |
| 10 | GPT-4.5 (Preview) | 67.54 | #260 |
| 11 | Gemini 2.0 Pro (Preview 02-05) | 65.79 | #318 |
| 12 | Doubao-1.5-pro-32k-250115 | 62.28 | #320 |
| 13 | DeepSeek V3 | 48.25 | #329 |
| 14 | DeepSeek R1 Distill Qwen 1.5B | 37.72 | #1521 |
| 15 | Phi-4 | 35.09 | #707 |
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-march-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.