Skip to content

Compare ​

Entries
MetricAgent Alpha · model-largeAgent Beta · model-largeAgent Beta · model-pro
Success rate71.4%67.8%74.6%
Cost per task$0.412$0.538$0.689
Time per task184 s231 s260 s
Success rate
Cost per task
Time per task
By category

Last updated:

Results are published as data alongside each benchmark.