Agent Task
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99Success Rate
57
Jul 7, 2026
86.7Success Rate
40
Jul 7, 2026
92.3TGC
29
Jun 16, 2026
100Accuracy
21
May 19, 2026
84.2Task Goal Completion (TGC)
21
Jun 16, 2026
99Success Rate (SR)
17
Feb 26, 2026
100Success Rate
17
Feb 26, 2026
100Success Rate
17
Feb 26, 2026
100Accuracy
16
May 21, 2026
44.98Success Rate
16
May 19, 2026
24.89Success Rate
16
May 19, 2026
98.4Success Rate @1
13
Jul 7, 2026
50.7Suc@1
13
Jul 7, 2026
67.5Success Rate
11
Apr 13, 2026
59.5Average Score
7
Mar 31, 2026
59Average Reward
7
Mar 10, 2026