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

Autonomous LLM training on PostTrainBench

63.75Score

Instruct

2.150818.142934.13550.1271Jun 30, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.06
63.75-
2026.06
49.41-
2026.06
46.58-
2026.06
44.81-
2026.06
32.6-
2026.06
27.09-
2026.06
25.91-
2026.06
25.67-
2026.06
25.6-
2026.06
24.88-
2026.06
24.2-
2026.06
24.01-
2026.06
23.96-
2026.06
23.88-
2026.06
22.32-
2026.06
22.08-
2026.06
21.76-
2026.06
21.2-
2026.06
20.01-
2026.06
19.51-
2026.06
17.01-
2026.06
16.9-
2026.06
16.72-
2026.06
15.82-
2026.06
15.18-
2026.06
14.77-
2026.06
14.34-
2026.06
10.43-
2026.06
8.14-
2026.06
6.66-
2026.06
4.6-
2026.06
4.52-
2026.06
-51.14
2026.06
-7.53
2026.06
-23.21
2026.06
-19.71
2026.06
-12.13
2026.06
-26.94
2026.06
-23.35
2026.06
-19.58