Benchmark
BrowserGym VisualWebArena
Vision benchmarks measure how well models understand images. Scores are percentages.
All vision benchmarksScores from BrowserGym Leaderboard.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 21.5%
- Mean
- 21%
- Median
- 4%
- Std dev
- 16.9%
- 10th percentile
- 26.7%
- 90th percentile
- 16.9%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 4oGenericAgent· BrowserGym Leaderboard | 26.7% |
| 2 | Claude 3.5 SonnetGenericAgent· BrowserGym Leaderboard | 21% |
| 3 | GPT-4o miniGenericAgent· BrowserGym Leaderboard | 16.9% |
Data credits: BrowserGym Leaderboard (ServiceNow), MIT (licence)