SuperCLUE General (August 2024) - Hard: leaderboard
SuperCLUE general leaderboard, August 2024 edition (2024年8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 | GPT-4 Turbo | 73.7 | #417 |
| 2 | Claude 3.5 Sonnet | 72.15 | #362 |
| 3 | Qwen 2 72B Instruct | 67.15 | #579 |
| 4 | Mistral Large 2 (Jul) | 66.98 | #490 |
| 5 | GPT-4o Mini | 66.93 | #598 |
| 6 | GLM-4 (0520) | 65.28 | #612 |
| 7 | Gemini 1.5 Pro | 64.71 | #454 |
| 8 | GPT-4 (0613) | 59.25 | #493 |
| 9 | Yi Large | 57.64 | #566 |
| 10 | Llama 3.1 405B Instruct | 56.92 | #470 |
| 11 | 360gpt2-pro | 56.38 | #557 |
| 12 | Llama 3.1 70B Instruct | 55.6 | #567 |
| 13 | Qwen Max | 53.16 | #388 |
| 14 | Yi-1.5-34B-Chat-16K | 46.87 | #822 |
| 15 | Gemma 2 9B (IT) | 46.85 | #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-general-august-2024-hard · How It Works · Data refreshed daily, snapshot 2026-11-05.