SuperCLUE General (December 2023) - Open-Ended Questions (OPEN): leaderboard
SuperCLUE general leaderboard, December 2023 edition (2023年12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. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 Turbo | 90.89 | #417 |
| 2 | GPT-4 | 76.24 | #459 |
| 3 | Claude 2 | 65.14 | #761 |
| 4 | Qwen-72B-Chat | 62.31 | #835 |
| 5 | Yi Chat 34B | 61.99 | #950 |
| 6 | Gemini 1.0 Pro | 59.33 | #900 |
| 7 | GPT-3.5 Turbo | 55.63 | #858 |
| 8 | Baichuan2-13B-Chat | 54.45 | #1210 |
| 9 | Qwen-14B-Chat | 52.04 | #1161 |
| 10 | chatglm3-6B | 42.3 | #1416 |
| 11 | Chinese-Alpaca-2-13B | 38.91 | #1390 |
| 12 | Llama 2 13B Chat | 34.91 | #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-december-2023-open-ended-questions-open · How It Works · Data refreshed daily, snapshot 2026-11-05.