Tool-use task completion
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
20Success Rate
16
Mar 4, 2026
0.26Avg Tokens (M)
16
Mar 4, 2026
84.4Success Rate
14
Jul 9, 2026
89.9Task Success Rate (TSR)
11
Apr 10, 2026
70Pass Rate
11
Apr 6, 2026
43.3Success Rate
7
Jul 9, 2026