Benchmarks · agentic
BU Bench V1 (Browser Use)
A browser agent completes 100 hand-selected web tasks: custom page-interaction challenges plus tasks drawn from WebBench, Mind2Web 2, GAIA and BrowseComp. Maintained by Browser Use. Score: Task success rate.
7 models · 7 results · data as of 2026-10-29 · github.com ↗
Leaderboard
Opus 4.8 max
All results
7 rows| # | Model | Effort | Score | Harness |
|---|---|---|---|---|
| 1 | Opus 4.8 | max | 85.0% | BrowserUseCloudAPI v4 · integrated browser |
| 2 | Opus 4.7 | max | 74.0% | BrowserUse 0.13.7 · BrowserUseCloud browser |
| 3 | GPT-5.5 | xhigh | 66.0% | BrowserUse 0.13.7 · BrowserUseCloud browser |
| 4 | Gemini 3.5 Flash | xhigh | 65.0% | BrowserUse 0.13.7 · BrowserUseCloud browser |
| 5 | Qwen 3.6 Plus | max | 45.0% | BrowserUse 0.13.7 · BrowserUseCloud browser |
| 6 | DeepSeek V4 Flash 0731 | max | 37.0% | BrowserUse 0.13.7 · BrowserUseCloud browser |
| 7 | GPT-5.6 Luna | max | 31.0% | BrowserUse 0.13.7 · BrowserUseCloud browser |