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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 40.52 |
| 2 | Claude Opus 5 | 38.9 |
| 3 | GPT-5.6 Sol | 37.32 |
| 4 | Kimi K3 | 30.26 |
| 5 | Grok 4.6 | 29.92 |
| 6 | Qwen 3.8 Max | 27.59 |
| 7 | Seed 2.1 Pro | 23.67 |
| 8 | MiniMax-M3 | 18.83 |
| 9 | MiMo-V2.5 | 17.93 |
| 10 | Gemini 3.1 Pro (Preview) | 16.46 |
| 11 | Qwen 3.5 Omni Plus | 11.86 |
| 12 | Seed 2.0 Lite | 11.7 |
| 13 | Muse Spark 1.1 | 10.14 |
| 14 | Qwen 3.8 27B | 7.56 |
Interactive version: theaggregate.ai/benchmark?slug=omni2web-direct-editing-fulfillment · How It Works · Data refreshed daily, snapshot 2026-09-26.