MEGA-Bench Task - Perception Test Video Character Order — leaderboard

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

Top models

#ModelScore
1GPT-4o93.8
2Gemma 3 12B (IT)93.8
3Gemini 1.5 Pro (002)93.8
4Gemini 2.5 Pro87.5
5Gemma 3 27B (IT)87.5
6Gemini 1.5 Flash (002)87.5
7Gemini 2.0 Flash (Preview)87.5
8InternVL3-78B81.2
9InternVL3-38B81.2
10GPT-4o Mini81.2
11InternVL2.5-78B81.2
12InternVL3-14B75
13Claude 3.5 Sonnet (20241022)75
14Claude 3.5 Sonnet (20240620)68.8
15InternVL3-8B62.5

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