MEGA-Bench Task - Video Segments Reordering — leaderboard

Metric: Task Score (%). Source: huggingface.co. 44 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro14.3
2InternVL3-38B14.3
3Gemini 2.0 Flash (Preview)14.3
4GPT-4o7.1
5InternVL3-14B7.1
6MiniCPM-V-2.67.1
7Claude 3.5 Sonnet (20240620)7.1
8Gemma 3 27B (IT)0
9Gemma 3 12B (IT)0
10Gemma 3 4B (IT)0
11InternVL3-78B0
12InternVL2-8B0
13InternVL3-8B0
14Qwen 2 VL 72B0
15Qwen 2 VL 7B0

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-video-segments-reordering · How the rankings work · Data refreshed daily, snapshot 2026-07-22.