SuperCLUE-Math6o (November 2024) - Overall: leaderboard
SuperCLUE-Math6o is a Chinese elementary-school math olympiad benchmark of competition problems. November 2024 edition (2024年11月): headline 总分 of the 总榜单 sheet. Each dated workbook is a separate evaluation round, kept apart from the current board. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Estimated already saturated. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 Preview (2024-09-12) | 73.5 | #214 |
| 2 | QwQ 32B-Preview | 61.35 | #671 |
| 3 | Gemini 1.5 Pro (002) | 54.58 | #368 |
| 4 | Qwen 2.5 72B Instruct | 50.03 | #469 |
| 5 | GLM-4 Plus | 45.88 | #398 |
| 6 | DeepSeek V2.5 | 45.28 | #494 |
| 7 | Step 2 16K | 45.27 | #442 |
| 8 | Claude 3.5 Sonnet | 44.97 | #362 |
| 9 | O1 Mini (2024-09-12) | 43.99 | #412 |
| 10 | GPT-4 Turbo | 42.7 | #417 |
| 11 | Qwen 2.5 7B Instruct | 37.39 | #863 |
| 12 | Llama 3.1 405B Instruct | 33.85 | #470 |
| 13 | GLM-4 9B Chat | 30.3 | #911 |
| 14 | Llama 3.1 70B Instruct | 30.17 | #567 |
| 15 | Gemma 2 9B (IT) | 26.81 | #795 |
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-november-2024-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.