SuperCLUE General (March 2025) - Math Reasoning: leaderboard
Metric: Score. Source: www.superclueai.com. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini (High) | 94.74 |
| 2 | QwQ-32B | 88.6 |
| 3 | DeepSeek R1 | 85.96 |
| 4 | DeepSeek R1 Distill Qwen 32B | 85.85 |
| 5 | Gemini 2.0 Flash (01-21) (Thinking) | 83.33 |
| 6 | DeepSeek R1 Distill Qwen 14B | 79.46 |
| 7 | Claude 3.7 Sonnet | 78.07 |
| 8 | DeepSeek-R1-Distill-Qwen-7B | 77.23 |
| 9 | GLM-Zero-Preview | 74.56 |
| 10 | GPT-4.5 (Preview) | 67.54 |
| 11 | Gemini 2.0 Pro (Preview 02-05) | 65.79 |
| 12 | Doubao-1.5-pro-32k-250115 | 62.28 |
| 13 | DeepSeek V3 | 48.25 |
| 14 | hunyuan-turbos-20250226 | 47.37 |
| 15 | DeepSeek R1 Distill Qwen 1.5B | 37.72 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-march-2025-math-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.