Omni2Web - Direct Editing Grounding: leaderboard

Metric: Target-grounding rate (%; Track A rubric items: the edited HTML changes the element each active step refers to; 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 July 2027. 15 models tracked.

Top models

#ModelScore
1Gemini 3.5 Flash59.2
2GPT-5.6 Sol55.92
3Claude Opus 554.11
4Qwen 3.8 Max43.51
5Kimi K343.32
6Grok 4.642.52
7Seed 2.1 Pro37.54
8MiMo-V2.531.44
9MiniMax-M331.12
10Gemini 3.1 Pro (Preview)26.93
11Muse Spark 1.122.29
12Qwen 3.5 Omni Plus20.79
13Seed 2.0 Lite20.38
14Qwen 3.8 27B12.25

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