VMLU - Other — leaderboard
Metric: Accuracy (%). Source: vmlu.ai. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | QwQ-32B | 70.62 |
| 2 | Llama 3 70B | 63.53 |
| 3 | GPT-4o Mini | 60.91 |
| 4 | GPT-4 | 60.37 |
| 5 | QwQ 32B-Preview | 59.58 |
| 6 | Gemma 2 9B (IT) | 54.44 |
| 7 | Qwen 2.5 7B Instruct | 54.4 |
| 8 | Phi-3-small-128k-instruct | 40.65 |
| 9 | gemma-7B (IT) | 40.11 |
| 10 | Phi-3-small-8k-instruct | 39.99 |
| 11 | Qwen-7B | 32.68 |
| 12 | Qwen 2 7B Instruct | 29.29 |
| 13 | gemma-2B (IT) | 26.81 |
| 14 | bloom-1b7 | 25.19 |
| 15 | falcon-7B | 24.73 |
Interactive version: theaggregate.ai/benchmark?slug=vmlu-other · How the rankings work · Data refreshed daily, snapshot 2026-07-22.