TCGBench

TCGBench is a benchmark designed to evaluate the thoroughness and effectiveness of test-case generation for code, facilitating the study of the test-case generation task in the context of large language models.

Papers using TCGBench (3)

Rethinking Verification for LLM Code Generation: From Generation to Testing2025Rethinking Verification for LLM Code Generation: From Generation to Testing2025Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems2025