Agentic Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.58Score
100
Feb 27, 2026
74.1Success Rate
59
Jun 17, 2026
76.02Success Rate
45
May 12, 2026
97.7Success Rate
21
Mar 27, 2026
72.3Org. Score
20
May 12, 2026
82.2Original Score
20
May 12, 2026
91Success Rate (Org.)
20
May 12, 2026
82.05Success Rate
20
May 12, 2026
86.06Average Score
17
Feb 26, 2026
91.3Score
16
Jun 16, 2026
82.3Success Rate
15
Mar 10, 2026
73.9Score
14
Jun 2, 2026
48.2Success Rate
12
Mar 10, 2026
38.3Success Rate
12
Mar 10, 2026
76Airline Score
9
Jul 7, 2026
31.5Accuracy
8
May 18, 2026
77.31Accuracy
8
Feb 26, 2026
41.6Overall Score
7
Feb 26, 2026
86.45Accuracy
6
May 20, 2026
97.2Pick Success Rate
5
May 13, 2026
18.4Accuracy
4
Apr 15, 2026
75.9Accuracy
3
May 8, 2026
84.7Accuracy
3
May 8, 2026
37.5Success Rate
3
Apr 15, 2026
26.8Success Rate
3
Apr 15, 2026