LocBench

LocBenchRR An MTEB dataset Massive Text Embedding Benchmark Software Issue Localization. Task category t2t Domains Programming, Written Reference https://arxiv.org/abs/2503.09089Source datasets: tarsur909/mteb-loc-bench-reranking How to evaluate on this task You can evaluate an embedding model on this dataset using the

Papers using LocBench (6)

FastCode: Fast and Cost-Efficient Code Understanding and Reasoning2026LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering2025LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering2025A Benchmark for Localizing Code and Non-Code Issues in Software Projects2025LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering2025SweRank: Software Issue Localization with Code Ranking2025