SuperCLUE General (June 2024) - Hard: leaderboard
SuperCLUE general leaderboard, June 2024 edition (2024年6月): Hard group score covering precise instruction following (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. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 85 | #357 |
| 2 | Claude 3.5 Sonnet | 84 | #362 |
| 3 | Qwen 2 72B Instruct | 79 | #579 |
| 4 | GLM-4 (0520) | 79 | #612 |
| 5 | DeepSeek V2 | 78 | #549 |
| 6 | GPT-4 Turbo | 74 | #417 |
| 7 | Llama 3 70B Instruct | 72 | #640 |
| 8 | GPT-4 | 70 | #459 |
| 9 | 360gpt2-pro | 69 | #557 |
| 10 | Gemini 1.5 Pro | 62 | #454 |
| 11 | GPT-3.5 Turbo (0125) | 59 | #975 |
| 12 | Yi-1.5-34B-Chat-16K | 52 | #822 |
| 13 | Qwen 2 7B Instruct | 51 | #982 |
| 14 | Llama 3 8B Instruct | 47 | #1116 |
| 15 | Yi-1.5-6B-Chat | 39 | #1241 |
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-june-2024-hard · How It Works · Data refreshed daily, snapshot 2026-11-05.