Agentic Search
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
58Average Token-level F1
30
Jun 2, 2026
90Accuracy
29
Jun 23, 2026
70.8Accuracy
21
Apr 16, 2026
52.3PopQA Accuracy
19
Jun 2, 2026
51.6NQ Accuracy
19
Jun 2, 2026
77.3Score
19
Jun 18, 2026
78Accuracy
18
Apr 21, 2026
48.6Accuracy
18
Apr 16, 2026
67.6Accuracy
16
Apr 21, 2026
63.9Accuracy
15
Jun 23, 2026
71.2Accuracy
15
Jun 23, 2026
59.3Accuracy
15
Jun 23, 2026
96.9Accuracy
14
Jun 2, 2026
61Accuracy
14
Jun 2, 2026
66.5Accuracy
14
Jun 2, 2026
13.5String-F1
14
Apr 7, 2026
36.6String-F1
14
Apr 7, 2026
21String-F1
14
Apr 7, 2026
73.1String-F1 Score
14
Apr 7, 2026
69.9String-F1
14
Apr 7, 2026
0.603String-F1
14
Apr 7, 2026
32.5String F1 Score
14
Apr 7, 2026
80.3Score
12
May 7, 2026
49.24LJFT
12
Feb 27, 2026
64.8LJFT Score
12
Feb 27, 2026