Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Search on XBench DeepSearch (Accuracy)

73Accuracy

Web2BigTable

24.74437.27249.862.328Apr 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
73
2026.04
72
2026.04
72
2026.04
71
2026.04
70
2026.04
70
2026.04
69
2026.04
69
2026.04
67
2026.04
66
2026.04
65
2026.04
64
2026.04
64
2026.04
62
2026.04
56
2026.04
54.6
2026.04
54.5
2026.04
53.3
2026.04
52
2026.04
50
2026.04
40
2026.04
35
2026.04
28
2026.04
26.6