Mind2Web-Live: leaderboard
A model plans the actions of the WebCanvas browser agent on 104 Mind2Web tasks run on the live websites; the score is the share of tasks in which every annotated key state was reached (a three-run mean for six of the models; the paper does not give the run count for the others). Unlike Mind2Web, which compares actions to a recorded trace offline, it checks intermediate states on the live site.
Metric: Task success rate on 104 live tasks (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 Preview (0125) | 23.1 | #1197 |
| 2 | GPT-4o (2024-05-13) | 22.1 | #735 |
| 3 | GPT-4 Turbo | 21.1 | #1008 |
| 4 | Claude 3 Sonnet (20240229) | 20.2 | #1983 |
| 5 | Qwen 1.5 110B Chat | 20.2 | #1790 |
| 6 | GPT-3.5 Turbo (0125) | 16.5 | #3575 |
| 7 | Claude 3 Haiku (20240307) | 16.3 | #2384 |
| 8 | Qwen 2 72B Instruct | 15.4 | #1523 |
| 9 | Qwen 1.5 72B Chat | 15.4 | #2220 |
| 10 | Claude 3 Opus (20240229) | 14.4 | #1158 |
| 11 | Mistral 7B Instruct (v0.3) | 11.7 | #6707 |
| 12 | Qwen 1.5 14B Chat | 10.6 | #3263 |
| 13 | Qwen 1.5 7B Chat | 10.6 | #6485 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=mind2web-live · How It Works · Data refreshed daily, snapshot 2026-11-17.