SuperCLUE General (October 2024) - Science: leaderboard
Metric: Score. Source: www.superclueai.com. 42 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Preview | 86.07 |
| 2 | Qwen 2.5 72B Instruct | 83.12 |
| 3 | 360gpt2-pro | 82.95 |
| 4 | Claude 3.5 Sonnet (20241022) | 82.48 |
| 5 | DeepSeek V2.5 | 81.7 |
| 6 | Claude 3.5 Sonnet (20240620) | 81.68 |
| 7 | GLM-4 Plus | 81.41 |
| 8 | GPT-4 Turbo | 80.78 |
| 9 | Llama 3.1 405B Instruct | 80.54 |
| 10 | Step 2 16K | 80.52 |
| 11 | Gemini 1.5 Pro (002) | 80.42 |
| 12 | GPT-4o Mini | 79.85 |
| 13 | Llama 3.1 70B Instruct | 77.52 |
| 14 | Llama 3.2 90B Instruct | 75.89 |
| 15 | Qwen 2.5 7B Instruct | 74.63 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-october-2024-science · How It Works · Data refreshed daily, snapshot 2026-09-19.