SuperCLUE General (August 2024) - Hard: leaderboard
Metric: Score. Source: www.superclueai.com. 42 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo | 73.7 |
| 2 | Claude 3.5 Sonnet | 72.15 |
| 3 | Qwen 2 72B Instruct | 67.15 |
| 4 | Mistral Large 2 (Jul) | 66.98 |
| 5 | GPT-4o Mini | 66.93 |
| 6 | GLM-4 (0520) | 65.28 |
| 7 | Gemini 1.5 Pro | 64.71 |
| 8 | GPT-4 (0613) | 59.25 |
| 9 | Yi Large | 57.64 |
| 10 | Llama 3.1 405B Instruct | 56.92 |
| 11 | 360gpt2-pro | 56.38 |
| 12 | Llama 3.1 70B Instruct | 55.6 |
| 13 | Qwen Max | 53.16 |
| 14 | Yi-1.5-34B-Chat-16K | 46.87 |
| 15 | Gemma 2 9B (IT) | 46.85 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-august-2024-hard · How It Works · Data refreshed daily, snapshot 2026-09-19.