🖼 Provide standardized evaluation tools for programming competition tasks for large language models (LLMs).

Provide a standardized evaluation tool for programming competition tasks for large language models (LLMs).

Support programming problems of various difficulty levels; seamlessly connect to mainstream LLM interfaces such as OpenAI; results can be submitted to the official email for evaluation.

LiveCodeBench-Pro | #Tool

via Black Hole Resource Notes - Telegram Channel