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

Task Success on SkillLearnBench Random

29Success Count

Revision v3

4.0410.521723.48May 31, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
2918
2026.05
2540
2026.05
2424
2026.05
236
2026.05
2232
2026.05
20-
2026.05
17-6
2026.05
168
2026.05
1520
2026.05
144
2026.05
12-
2026.05
1114.83
2026.05
108
2026.05
86
2026.05
7-
2026.05
70
2026.05
70
2026.05
74
2026.05
6-
2026.05
5-