SuperCLUE General (February 2024) - Open-Ended Questions (OPEN): leaderboard
SuperCLUE general leaderboard, February 2024 edition (2024年2月): OPEN multi-turn open-ended question score covering language and knowledge, professional skills, tool use and traditional safety (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. 29 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4 | 87.49 | #647 |
| 2 | Qwen 1.5 72B Chat | 78.39 | #782 |
| 3 | Claude 2 | 72.9 | #761 |
| 4 | Qwen 1.5 14B Chat | 67.9 | #976 |
| 5 | GPT-3.5 Turbo (0125) | 63.26 | #975 |
| 6 | Yi Chat 34B | 59.99 | #950 |
| 7 | Gemini 1.0 Pro | 58.96 | #900 |
| 8 | Qwen 1.5 7B Chat | 57.7 | #1292 |
| 9 | Qwen-14B-Chat | 54.98 | #1161 |
| 10 | Baichuan2-13B-Chat | 53.99 | #1210 |
| 11 | chatglm3-6B | 34.33 | #1416 |
| 12 | Llama 2 13B Chat | 30.38 | #1414 |
| 13 | Chinese-Alpaca-2-13B | 29.43 | #1390 |
| 14 | gemma-7B (IT) | 23.04 | #1477 |
| 15 | Llama 2 7B Chat | 16.06 | #1478 |
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-february-2024-open-ended-questions-open · How It Works · Data refreshed daily, snapshot 2026-11-05.