VMLU - Other — leaderboard

Metric: Accuracy (%). Source: vmlu.ai. 25 models tracked.

Top models

#ModelScore
1QwQ-32B70.62
2Llama 3 70B63.53
3GPT-4o Mini60.91
4GPT-460.37
5QwQ 32B-Preview59.58
6Gemma 2 9B (IT)54.44
7Qwen 2.5 7B Instruct54.4
8Phi-3-small-128k-instruct40.65
9gemma-7B (IT)40.11
10Phi-3-small-8k-instruct39.99
11Qwen-7B32.68
12Qwen 2 7B Instruct29.29
13gemma-2B (IT)26.81
14bloom-1b725.19
15falcon-7B24.73

Interactive version: theaggregate.ai/benchmark?slug=vmlu-other · How the rankings work · Data refreshed daily, snapshot 2026-07-22.