WebRetriever (Protocol I, Navigation): leaderboard
WebRetriever (2026) Protocol I: web agents must reach the target page for 1,000 user tasks on live consumer, professional and enterprise websites, starting from a fixed entry URL without search engines. Human-judged success rate in percent, higher is better.
Metric: Success rate (%; 1,000 tasks, reaching the target page for a user task; live websites from WebRetriever (800 sites across consumer, professional and enterprise domains), each task starting from a fixed entry URL with search engines blocked, Playwright-based online harness; task success judged by human annotators). Source: arxiv.org. Saturation forecast: Around April 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o (2024-08-06) | 24 | #740 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=webretriever-protocol-i-navigation · How It Works · Data refreshed daily, snapshot 2026-11-13.