Deep search
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.9Accuracy
59
May 29, 2026
81.3Score
50
Apr 15, 2026
91.3Pass@1
42
Feb 26, 2026
74.9Score
38
Mar 31, 2026
66.6Accuracy
35
May 29, 2026
58.1Accuracy
27
Feb 26, 2026
49.7Accuracy
27
Feb 26, 2026
75Accuracy
26
Feb 26, 2026
73Accuracy
24
May 1, 2026
70.9Accuracy
24
Feb 26, 2026
52Accuracy
24
May 29, 2026
55Success Rate
23
Jun 11, 2026
59Success Rate
22
Jun 11, 2026
68Success Rate
22
Jun 11, 2026
82Score
20
Mar 31, 2026
75Accuracy
16
May 29, 2026
11.4Accuracy
16
Jul 1, 2026
67.6Score
15
Apr 15, 2026
75Score
14
Feb 26, 2026
40.8Score
14
Feb 26, 2026
0.757Score
14
Feb 26, 2026
75Score (%)
14
Feb 26, 2026
70Score
13
Feb 26, 2026
75Score
12
Mar 31, 2026
41.44Score
11
Feb 26, 2026