Ego2Web (Caption Input): leaderboard
Metric: Success rate (%) on Ego2Web's 500 web tasks grounded in Ego4D egocentric videos (e-commerce, media retrieval, knowledge lookup, maps and others) on live websites, judged by three human annotators with majority vote, at most 40 steps per task; computer-use agents that cannot take video get a detailed timestamped caption of it written by Gemini-3.1-Pro instead; higher is better. Source: arxiv.org. Saturation forecast: Around February 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 30.6 | #76 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=ego2web-caption-input · How It Works · Data refreshed daily, snapshot 2026-10-11.