Omni2Web - Direct Editing: leaderboard
Metric: Edit Fidelity Score (%; Track A: 0.10 target grounding + 0.50 edit fulfillment + 0.20 no-damage + 0.20 revision handling per instance, averaged over 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 2028. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 51.17 |
| 2 | Claude Opus 5 | 47.37 |
| 3 | GPT-5.6 Sol | 42.86 |
| 4 | Grok 4.6 | 41.45 |
| 5 | Kimi K3 | 40.63 |
| 6 | Qwen 3.8 Max | 38.6 |
| 7 | Seed 2.1 Pro | 34.48 |
| 8 | Gemini 3.1 Pro (Preview) | 34.08 |
| 9 | Qwen 3.5 Omni Plus | 29.56 |
| 10 | MiniMax-M3 | 29.49 |
| 11 | MiMo-V2.5 | 28.79 |
| 12 | Seed 2.0 Lite | 28.33 |
| 13 | Qwen 3.8 27B | 26.94 |
| 14 | Muse Spark 1.1 | 24.08 |
Interactive version: theaggregate.ai/benchmark?slug=omni2web-direct-editing · How It Works · Data refreshed daily, snapshot 2026-09-26.