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.
BU Bench V1 (Browser Use)
Higher is better · best effort per model
full table below
| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Opus 4.8 | max | 85.0% |
| 2 | Opus 4.7 | max | 74.0% |
| 3 | GPT-5.5 | xhigh | 66.0% |
| 4 | Gemini 3.5 Flash | xhigh | 65.0% |
| 5 | Qwen 3.6 Plus | max | 45.0% |
| 6 | DeepSeek V4 Flash 0731 | max | 37.0% |
| 7 | GPT-5.6 Luna | max | 31.0% |