SuperCLUE General (November 2023) - Open-Ended Questions (OPEN): leaderboard
SuperCLUE general leaderboard, November 2023 edition (2023年11月): OPEN multi-turn open-ended question score covering language understanding and generation, professional skills and knowledge, 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. 21 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 Turbo | 97.53 | #417 |
| 2 | GPT-4 | 73.01 | #459 |
| 3 | Yi Chat 34B | 71.21 | #950 |
| 4 | Claude 2 | 57.82 | #761 |
| 5 | GPT-3.5 Turbo | 57.16 | #858 |
| 6 | Baichuan2-13B-Chat | 50.33 | #1210 |
| 7 | Qwen-14B-Chat | 49.05 | #1161 |
| 8 | MiniMax-abab5.5 | 45.27 | #1030 |
| 9 | Chinese-Alpaca-2-13B | 38.09 | #1390 |
| 10 | chatglm3-6B | 38.01 | #1416 |
| 11 | Llama 2 13B Chat | 28.67 | #1414 |
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-november-2023-open-ended-questions-open · How It Works · Data refreshed daily, snapshot 2026-11-05.