SuperCLUE-CoT (October 2024) - Overall: leaderboard
SuperCLUE-CoT evaluates chain-of-thought reasoning of Chinese LLMs, judging both answer quality and the reasoning chain with its reflection. October 2024 edition (2024年10月): headline 总分 of the 总榜 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. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 | 76.12 | #190 |
| 2 | O1 Preview (2024-09-12) | 71.84 | #214 |
| 3 | QwQ 32B-Preview | 63.5 | #671 |
| 4 | DeepSeek R1 | 62.04 | #262 |
| 5 | Claude 3.5 Sonnet | 54.6 | #362 |
| 6 | Gemini 1.5 Pro (002) | 54.36 | #368 |
| 7 | GLM-4 Plus | 50.19 | #398 |
| 8 | Yi Lightning | 49.98 | #429 |
| 9 | GPT-4 Turbo | 48.52 | #417 |
| 10 | Qwen 2.5 72B Instruct | 46.01 | #469 |
| 11 | DeepSeek V2.5 | 43.53 | #494 |
| 12 | O1 Mini (2024-09-12) | 43.29 | #412 |
| 13 | Step 2 16K | 40.86 | #442 |
| 14 | ERNIE-4.0-Turbo-8K-Preview | 38.18 | #603 |
| 15 | Llama 3.1 405B Instruct | 37.82 | #470 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-cot-october-2024-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.