Tool Use Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88API Success Rate
28
May 19, 2026
52.78Solve Precision (P)
27
Apr 16, 2026
61.31Mean Accuracy @16
24
May 28, 2026
47.97Accuracy
20
Jun 11, 2026
66.73Accuracy
20
May 26, 2026
62.6Accuracy
14
Jun 9, 2026
63.9Avg Accuracy
14
Feb 26, 2026
60.1Accuracy
13
Jun 9, 2026
18Average Performance
6
Jun 18, 2026
33.33Success Rate
5
May 11, 2026
59.36Success Rate
5
May 11, 2026
52.67Success Rate
5
May 11, 2026