Text-based agent interaction
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.5Accuracy
14
May 13, 2026
81.5Accuracy
14
May 13, 2026
88Accuracy
14
May 13, 2026
76Accuracy
6
May 13, 2026
81Accuracy
6
May 13, 2026
88Accuracy
6
May 13, 2026