DyCodeEval (ICML 2025) enables dynamic benchmarking for code LLMs. This collection features dynamic HumanEval and MBPP sets generated with Claude 3.5.
Simin Chen
CM
AI & ML interests
None yet
Organizations
datasets 12
CM/humaneval_trans_java_python
Viewer • Updated • 164 • 32
CM/Dynamic_LeetCode
Viewer • Updated • 2.87k • 83
CM/Dynamic_MBPP_sanitized
Viewer • Updated • 15.8k • 7
CM/Dynamic_HumanEvalZero
Viewer • Updated • 15.7k • 8
CM/codexglue_codetrans
Viewer • Updated • 11.8k • 64 • 2
CM/codexglue_code2text_ruby
Viewer • Updated • 27.6k • 1.47k • 1
CM/codexglue_code2text_python
Viewer • Updated • 281k • 2.43k • 8
CM/codexglue_code2text_php
Viewer • Updated • 268k • 1.41k • 2
CM/codexglue_code2text_javascript
Viewer • Updated • 65.2k • 1.57k • 12
CM/codexglue_code2text_java
Viewer • Updated • 181k • 1.83k • 4