SuperCLUE General (October 2024) - Hard: leaderboard
SuperCLUE general leaderboard, October 2024 edition (2024年10月): Hard group score covering instruction following and advanced reasoning (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 | 64.89 | #205 |
| 2 | Claude 3.5 Sonnet (20241022) | 53.6 | #302 |
| 3 | GLM-4 Plus | 51.09 | #398 |
| 4 | Gemini 1.5 Pro (002) | 47.82 | #368 |
| 5 | GPT-4 Turbo | 46.82 | #417 |
| 6 | Qwen 2.5 72B Instruct | 46.64 | #469 |
| 7 | Claude 3.5 Sonnet (20240620) | 46.49 | #308 |
| 8 | Llama 3.1 405B Instruct | 45.46 | #470 |
| 9 | Step 2 16K | 43.91 | #442 |
| 10 | 360gpt2-pro | 43.68 | #557 |
| 11 | DeepSeek V2.5 | 43.5 | #494 |
| 12 | ERNIE-4.0-Turbo-8K-Preview | 41.7 | #603 |
| 13 | GPT-4o Mini | 41.46 | #598 |
| 14 | Llama 3.1 70B Instruct | 37.71 | #567 |
| 15 | Llama 3.2 90B Instruct | 36.84 | #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-hard · How It Works · Data refreshed daily, snapshot 2026-11-05.