SuperCLUE General (October 2024) - Science: leaderboard
SuperCLUE general leaderboard, October 2024 edition (2024年10月): science group (理科) score covering computation, logical reasoning, code and tool use (总排行榜 sheet). SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Estimated already saturated. 42 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 Preview | 86.07 | #205 |
| 2 | Qwen 2.5 72B Instruct | 83.12 | #469 |
| 3 | 360gpt2-pro | 82.95 | #557 |
| 4 | Claude 3.5 Sonnet (20241022) | 82.48 | #302 |
| 5 | DeepSeek V2.5 | 81.7 | #494 |
| 6 | Claude 3.5 Sonnet (20240620) | 81.68 | #308 |
| 7 | GLM-4 Plus | 81.41 | #398 |
| 8 | GPT-4 Turbo | 80.78 | #417 |
| 9 | Llama 3.1 405B Instruct | 80.54 | #470 |
| 10 | Step 2 16K | 80.52 | #442 |
| 11 | Gemini 1.5 Pro (002) | 80.42 | #368 |
| 12 | GPT-4o Mini | 79.85 | #598 |
| 13 | ERNIE-4.0-Turbo-8K-Preview | 78.69 | #603 |
| 14 | Llama 3.1 70B Instruct | 77.52 | #567 |
| 15 | Llama 3.2 90B Instruct | 75.89 | #595 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-october-2024-science · How It Works · Data refreshed daily, snapshot 2026-11-05.