MEDit-Bench: leaderboard

Metric: mIoU (%; temporal IoU between the union of the predicted cuts and the union of the reference cuts, averaged over the 540 video, message and reference-edit triplets (60 long-form videos, three editing messages each, three professional edits per message); zero-shot: the model maps the video and the message to a sequence of cuts). Source: arxiv.org. Saturation forecast: Around 2031. 9 models tracked.

Top models

#ModelScore
1GPT-525.3
2Gemini 3 Pro23.5
3Qwen 3 VL 32B22.7
4GPT-5 Mini18.6
5Gemma 4 E4B (Non-reasoning)16.9
6Gemini 2.5 Pro15.2
7InternVL3.5-8B8

Interactive version: theaggregate.ai/benchmark?slug=medit-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.