SuperCLUE-MathCLUE - Overall: leaderboard
MathCLUE is built from Chinese National High School Mathematics Competition problems. Headline board of the newest workbook the superclueai.com vertical lists; score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Estimated already saturated. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 92.54 | #126 |
| 2 | O4 Mini (High) | 91.47 | #185 (O4 Mini) |
| 3 | QwQ-32B | 91.04 | #422 |
| 4 | Qwen 3 32B | 90.3 | #449 |
| 5 | O3 Mini (High) | 89.55 | #282 (O3 Mini) |
| 6 | DeepSeek R1 | 87.31 | #262 |
| 7 | Qwen 3 235B A22B | 85.71 | #323 |
| 8 | Qwen 3 30B A3B | 85.07 | #496 |
| 9 | Gemini 2.0 Flash (Thinking) | 80.6 | #351 (Gemini 2.0 Flash) |
| 10 | O1 | 77.61 | #190 |
| 11 | Claude 3.7 Sonnet (Thinking) | 69.4 | #259 (Claude 3.7 Sonnet) |
| 12 | GLM-Zero-Preview | 69.4 | #682 |
| 13 | DeepSeek V3 (0324) | 67.91 | #349 |
| 14 | QwQ 32B-Preview | 67.91 | #671 |
| 15 | GPT-4.1 | 50.57 | #258 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-mathclue-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.