Agentic
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78.4Score
27
Feb 26, 2026
91.6Score
20
Jul 7, 2026
70.64pass@1
16
Jun 16, 2026
48.31Pass@1
11
Jul 7, 2026
73.8Score
10
Jul 7, 2026
64.56Score
7
Jun 16, 2026
1,462Elo Score
7
Feb 26, 2026
5,478Score
7
Feb 26, 2026
46.3Score
7
Feb 26, 2026
68Overall Score
7
Feb 26, 2026
76.1Score
7
Feb 26, 2026
56.9Airline Score
5
Jul 7, 2026
25.5Accuracy
5
Jul 7, 2026
59.5Accuracy
4
Jul 7, 2026
82.1Score
4
May 8, 2026
69.2Pass@1
4
Mar 20, 2026