LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
- 980
- Python
- MIT
- 16 mo ago
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
Exploring and improving the quality of ChatGPT-generated code for LeetCode programming tasks.
A multimodal support-to-engineering agent that investigates bug reports, reproduces issues, patches code, and verifies fixes. Winner of the Enterprise Impact track at the Cerebras × Google DeepMind hackathon.
Text generation model, used with peft.