Agentic Capability
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.64Average Accuracy
8
Jun 29, 2026
54.05Accuracy
8
Jun 29, 2026
74.41Accuracy
8
Jun 29, 2026
90.45Accuracy
8
Jun 29, 2026
89Pass@1
7
Mar 20, 2026
23Pass@1
7
Mar 20, 2026