MEGA-Bench Task - MFC Bench Check Clip Stable Diffusion Generate: leaderboard

Metric: Task Score (%). Source: huggingface.co. 27 models tracked.

Top models

#ModelScore
1Pixtral-12B64.3
2InternVL2.5-2B57.1
3InternVL2-8B50
4Gemini 1.5 Pro (002)50
5GPT-4o42.9
6Claude 3.5 Sonnet (20241022)42.9
7Qwen 2 VL 2B42.9
8Aquila-VL-2B42.9
9Gemini 1.5 Flash (002)42.9
10Claude 3.5 Sonnet (20240620)42.9
11Qwen 2 VL 7B35.7
12GPT-4o Mini35.7
13InternVL2.5-78B35.7
14Qwen 2 VL 72B28.6

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-mfc-bench-check-clip-stable-diffusion-generate · How It Works · Data refreshed daily, snapshot 2026-09-05.