CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding

By Fu-Wei Zhang, Yanzhao Zhang, Mingxin Li, Dingkun Long, Lexiang Hu, Pengjun Xie, Zhao-Xiang Zhang, Fuzhen Zhuang. 2026

Subfields: Information Retrieval & Search, Evaluation & Benchmarks, Code Generation & Program Synthesis

Citations in the corpus

• Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents (2026, unknown): “CORE-Bench evaluates code retrieval for agentic coding across code understanding, issue-to-edit localization, and broader context retrieval [19].”