Multi-turn Agent Interaction
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
71.58Success Rate (SR)
39
Jun 29, 2026
89.06Success Rate
39
Jun 29, 2026
100Success Rate (Pick)
31
May 27, 2026
29.5Score
16
Jun 16, 2026
40.8Success Rate (SR)
16
Jun 16, 2026
43.57Success Rate (SR)
16
Jun 16, 2026