SuperCLUE General (October 2024) - Overall: leaderboard
SuperCLUE general leaderboard, October 2024 edition (2024年10月): overall score (总分) combining the science, liberal-arts and Hard groups (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 | 75.85 | #205 |
| 2 | Claude 3.5 Sonnet (20241022) | 70.88 | #302 |
| 3 | GLM-4 Plus | 69.64 | #398 |
| 4 | Qwen 2.5 72B Instruct | 68.9 | #469 |
| 5 | Claude 3.5 Sonnet (20240620) | 68.23 | #308 |
| 6 | Gemini 1.5 Pro (002) | 68.19 | #368 |
| 7 | GPT-4 Turbo | 67.48 | #417 |
| 8 | 360gpt2-pro | 67.19 | #557 |
| 9 | Step 2 16K | 67.02 | #442 |
| 10 | DeepSeek V2.5 | 66.87 | #494 |
| 11 | Llama 3.1 405B Instruct | 65.84 | #470 |
| 12 | ERNIE-4.0-Turbo-8K-Preview | 64.93 | #603 |
| 13 | GPT-4o Mini | 64.85 | #598 |
| 14 | Llama 3.1 70B Instruct | 61.62 | #567 |
| 15 | Qwen 2.5 7B Instruct | 60.61 | #863 |
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-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.