Agentic Task Execution
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.4Success Rate (SR)
15
Jun 11, 2026
44Success Rate (SR)
12
Jun 11, 2026
61.5Success Rate
11
Jun 11, 2026
78.5BU
6
Feb 26, 2026
86.7BU
6
Feb 26, 2026
91.2BU
6
Feb 26, 2026
76.5BU
6
Feb 26, 2026