SuperCLUE-Math6o - Overall: leaderboard
SuperCLUE-Math6o is an elementary-school math olympiad benchmark of 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. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek R1 | 82.15 | #262 |
| 2 | O1 | 75.98 | #190 |
| 3 | O1 Preview (2024-09-12) | 73.74 | #214 |
| 4 | QwQ 32B-Preview | 66.84 | #671 |
| 5 | Gemini 1.5 Pro (002) | 55.47 | #368 |
| 6 | Qwen 2.5 72B Instruct | 50.36 | #469 |
| 7 | Claude 3.5 Sonnet | 47.41 | #362 |
| 8 | DeepSeek V2.5 | 47.34 | #494 |
| 9 | Step 2 16K | 46.36 | #442 |
| 10 | GLM-4 Plus | 46.04 | #398 |
| 11 | O1 Mini (2024-09-12) | 44.03 | #412 |
| 12 | Qwen 2.5 7B Instruct | 39.94 | #863 |
| 13 | Llama 3.1 405B Instruct | 37.2 | #470 |
| 14 | GLM-4 9B Chat | 31.62 | #911 |
| 15 | Llama 3.1 70B Instruct | 30.93 | #567 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-math6o-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.