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

Code Evaluation on CodeMMLU software principles

24.9Accuracy

DPO + RM

12.62815.8141922.186Apr 7, 2025
Updated 18d ago

Evaluation Results

MethodLinks
2025.04
24.90.9
2025.04
23.10.7
2025.04
23.10.8
2025.04
230.9
2025.04
20.91
2025.04
20.30.7
2025.04
17.42.1
2025.04
17.42.4
2025.04
17.31.8
2025.04
15.32
2025.04
15.21.8
2025.04
13.11.9