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

Deep Research on xBench-DS-2505

82Score

SMTL-30B-300

32.39245.27158.1571.029Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
82
2026.04
78
2026.04
77.8
2026.04
75
2026.04
74.7
2026.04
74
2026.04
73.7
2026.04
72
2026.04
70
2026.04
69
2026.04
68.7
2026.04
67
2026.04
65
2026.04
62
2026.04
53.7
2026.04
50.5
2026.04
49
2026.04
48.5
2026.04
48
2026.04
38
2026.04
35
2026.04
34.3