Agent Task Completion
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.2Success Rate
31
Jun 4, 2026
0.704Avg Task Reward
27
Feb 26, 2026
0.921Average Task Reward
27
Feb 26, 2026
0.791Average Task Reward
27
Feb 26, 2026
76Product & Collaboration Score
17
Apr 30, 2026
88.7Pass@1
17
Apr 30, 2026
58.7Average Pass Rate
9
May 29, 2026
22.6Pass Rate
9
May 29, 2026
67Pass Rate
9
May 29, 2026
60Pass Rate
9
May 29, 2026
19Success Rate
8
Jun 4, 2026
83.7TGC Success Rate (N)
7
May 15, 2026
49.2Success Rate @ 1
4
Jun 29, 2026
66.1Accuracy (%)
4
Jun 24, 2026
60.1Accuracy
4
Jun 24, 2026
0.67Average Task Reward
2
Feb 26, 2026
92.1Avg Task Reward
2
Feb 26, 2026