Benchmark
Browser Use Benchmark
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.43
Score distribution
- 53%
- Mean
- 65%
- Median
- 16.1%
- Std dev
- 37%
- 10th percentile
- 74%
- 90th percentile
- 31%
- Min
This benchmark has a weight of 0.43 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7BrowserUse 0.13.7· Browser Use Benchmark data | 74% |
| 2 | GPT 5.5BrowserUse 0.13.7· Browser Use Benchmark data | 66% |
| 3 | Gemini 3.5 FlashBrowserUse 0.13.7· Browser Use Benchmark data | 65% |
| 4 | Qwen3.6 PlusBrowserUse 0.13.7· Browser Use Benchmark data | 45% |
| 5 | DeepSeek V4 Flash 0731BrowserUse 0.13.7· Browser Use Benchmark data | 37% |
| 6 | GPT-5.6 LunaBrowserUse 0.13.7· Browser Use Benchmark data | 31% |