SuperCLUE General (October 2023) - Objective Questions (OPT): leaderboard
SuperCLUE general leaderboard, October 2023 edition (2023年10月): OPT objective question score covering basic abilities, Chinese-specific knowledge and academic/professional abilities (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 | 85.6 | #459 |
| 2 | Qwen-14B-Chat | 77.78 | #1161 |
| 3 | MiniMax-abab5.5 | 76.72 | #1030 |
| 4 | Baichuan2-13B-Chat | 70.09 | #1210 |
| 5 | Claude 2 | 68.48 | #761 |
| 6 | GPT-3.5 | 68.13 | #825 |
| 7 | ChatGLM2 6B | 61.45 | #1475 |
| 8 | Chinese-Alpaca-2-13B | 55.26 | #1390 |
| 9 | Llama 2 13B Chat | 40.28 | #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-october-2023-objective-questions-opt · How It Works · Data refreshed daily, snapshot 2026-11-05.