Multi-Turn Tool Calling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
48Success Rate
20
Jun 25, 2026
38Airline Score
19
May 1, 2026
55.5Base Performance
15
Jun 4, 2026
85Overall Accuracy
15
Feb 26, 2026
15End-to-End Success Rate
6
Jun 15, 2026