Tool-Use Agent Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
48Base Rate
18
Mar 4, 2026
78Pass@4 Success Rate
12
Jun 30, 2026
76Pass@1
12
Jun 19, 2026
57.5Pass@4 Success Rate
6
Jun 30, 2026
44.173Pass@1 Success Rate
6
Apr 29, 2026
43.9Pass@1
4
Mar 17, 2026
42.5Pass@1
4
Mar 17, 2026
57.5Pass@1 Success Rate
4
Mar 17, 2026
37.6Pass@1 Success Rate
3
Apr 29, 2026