MEGA-Bench Task - Video Segments Reordering: leaderboard

The "Video Segments Reordering" subtask of MEGA-Bench Task. A single task from MEGA-Bench, a large-scale multimodal evaluation suite that scores vision-language models across 500+ real-world tasks spanning perception, reasoning, OCR, charts, documents, and multi-image understanding.

Metric: Task Score (%). Source: huggingface.co. Saturation forecast: Around September 2027. 44 models tracked.

Top models

#ModelScoreOverall rank
1InternVL3-38B14.3#405
2Gemini 2.5 Pro (Preview 03-25)14.3#123
3GLM-4.1V-9B (Thinking)14.3#472 (GLM-4.1V-9B)
4Gemini 2.0 Flash (Preview)14.3#370
5GPT-4o7.1#343
6Claude 3.5 Sonnet (20240620)7.1#299
7MiniCPM-V-2.67.1#836
8InternVL3-14B7.1#505
9Gemma 3 27B (IT)0#523
10Gemma 3 12B (IT)0#664
11Gemma 3 4B (IT)0#992
12GPT-4o Mini0#599
13Claude 3.5 Sonnet (20241022)0#291
14InternVL3-8B0#620
15Gemini 1.5 Pro (002)0#349

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-video-segments-reordering · How It Works · Data refreshed daily, snapshot 2026-10-20.