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

Skill Evolution on S-Bench

54.8Accuracy

ALIGNEVOSKILL

1.55215.37629.243.024Jun 29, 2025
Updated 7d ago

Evaluation Results

MethodLinks
2025.06
54.8-
2025.06
52.4-
2025.06
51.2-
2025.06
50-
2025.06
48.8-
2025.06
46.4-
2025.06
45.2-
2025.06
45.2-
2025.06
42.9-
2025.06
39.3-
2025.06
34.5-
2025.06
32.1-
2025.06
31-
2025.06
31-
2025.06
29.8-
2025.06
28.6-
2025.06
28.6-
2025.06
27.4-
2025.06
26.2-
2025.06
26.2-
2025.06
26.2-
2025.06
25-
2025.06
25-
2025.06
23.8-
2025.06
23.8-
2025.06
23.8-
2025.06
22.6-
2025.06
22.6-
2025.06
22.6-
2025.06
22.6-
2025.06
21.4-
2025.06
19-
2025.06
19-
2025.06
16.7-
2025.06
15.5-
2025.06
14.3-
2025.06
13.1-
2025.06
9.5-
2025.06
9.5-
2025.06
3.6-