SuperCLUE General (October 2024) - Liberal Arts: leaderboard
SuperCLUE general leaderboard, October 2024 edition (2024年10月): liberal-arts group (文科) score covering role play, generation and creation, language understanding, long text, knowledge 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. 42 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 76.96 | #469 |
| 2 | Step 2 16K | 76.65 | #442 |
| 3 | O1 Preview | 76.6 | #205 |
| 4 | Claude 3.5 Sonnet (20241022) | 76.56 | #302 |
| 5 | Claude 3.5 Sonnet (20240620) | 76.54 | #308 |
| 6 | GLM-4 Plus | 76.44 | #398 |
| 7 | Gemini 1.5 Pro (002) | 76.32 | #368 |
| 8 | DeepSeek V2.5 | 75.42 | #494 |
| 9 | 360gpt2-pro | 74.94 | #557 |
| 10 | GPT-4 Turbo | 74.85 | #417 |
| 11 | ERNIE-4.0-Turbo-8K-Preview | 74.4 | #603 |
| 12 | Qwen 2.5 7B Instruct | 73.28 | #863 |
| 13 | GPT-4o Mini | 73.24 | #598 |
| 14 | GLM-4 9B Chat | 71.94 | #911 |
| 15 | Llama 3.1 405B Instruct | 71.53 | #470 |
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-2024-liberal-arts · How It Works · Data refreshed daily, snapshot 2026-11-05.