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

Skill Evolution on SRA-Bench

77.3Accuracy

ALIGNEVOSKILL

42.25251.35160.4569.549Jun 29, 2025
Updated 7d ago

Evaluation Results

MethodLinks
2025.06
77.3-
2025.06
75.7-
2025.06
75.3-
2025.06
75.1-
2025.06
74.9-
2025.06
73.7-
2025.06
73.2-
2025.06
72.6-
2025.06
72.2-
2025.06
70.7-
2025.06
69.8-
2025.06
69.2-
2025.06
68.9-
2025.06
68.6-
2025.06
68.1-
2025.06
67.8-
2025.06
66.4-
2025.06
65.8-
2025.06
65.7-
2025.06
65.3-
2025.06
64.8-
2025.06
64.2-
2025.06
64.1-
2025.06
62.4-
2025.06
60.2-
2025.06
60-
2025.06
59.3-
2025.06
58.6-
2025.06
58-
2025.06
57.9-
2025.06
55.9-
2025.06
55.5-
2025.06
54.9-
2025.06
53.6-
2025.06
52.1-
2025.06
51.8-
2025.06
51.5-
2025.06
50.3-
2025.06
47.3-
2025.06
43.6-