Omni2Web - Direct Editing Fulfillment: leaderboard

Metric: Edit-fulfillment rate (%; Track A rubric items: each active step's requested change is realised in the edited HTML; 918 bilingual screen recordings of weakly referential webpage edit requests (speech plus cursor), 13,907 edit steps; the model edits the source HTML directly from the recording under its native input interface (omni: audio-visual video; vision-language: video or 1 fps frames plus manual transcript); rubric items judged by Gemini 3.1 Pro; unusable outputs score zero). Source: arxiv.org. Saturation forecast: Around February 2028. 15 models tracked.

Top models

#ModelScore
1Gemini 3.5 Flash40.52
2Claude Opus 538.9
3GPT-5.6 Sol37.32
4Kimi K330.26
5Grok 4.629.92
6Qwen 3.8 Max27.59
7Seed 2.1 Pro23.67
8MiniMax-M318.83
9MiMo-V2.517.93
10Gemini 3.1 Pro (Preview)16.46
11Qwen 3.5 Omni Plus11.86
12Seed 2.0 Lite11.7
13Muse Spark 1.110.14
14Qwen 3.8 27B7.56

Interactive version: theaggregate.ai/benchmark?slug=omni2web-direct-editing-fulfillment · How It Works · Data refreshed daily, snapshot 2026-09-26.