Multi-turn tool-use
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
68Average Success Rate
48
Jun 18, 2026
63.6Avg@4
25
Feb 26, 2026
36.9Average Success Rate
18
Jun 16, 2026
27.5Multi-Turn Success Rate
18
Jun 16, 2026
42.41Solve Rate (R)
18
Jun 16, 2026
75.1Pass@1
18
Feb 26, 2026
58.1Pass@1
18
Feb 26, 2026
50.9Pass@1
18
Feb 26, 2026
76.4Pass@1
18
Feb 26, 2026
60.2Pass@1
4
Jun 12, 2026
27Task Goal Completion (TGC)
3
Jun 12, 2026