WebArena: leaderboard
Self-hosted environment with 812 web tasks across e-commerce, forums, code repos, and CMS. Tests autonomous web navigation and interaction.
Metric: Success Rate (%). Source: webarena.dev. Source: docs.google.com. Saturation forecast: Around January 2027. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Median Human | 78.24 | |
| 2 | DeepSeek V3.2 | 74.3 | #205 |
| 3 | GPT-4 | 20.2 | #438 |
| 4 | GPT-4 (0613) | 14.9 | #491 |
| 5 | GPT-4o (2024-05-13) | 13.1 | #325 |
| 6 | Gemini 1.0 Pro | 7.12 | #933 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=webarena · How It Works · Data refreshed daily, snapshot 2026-10-20.