LongCodeQA

The 'LongCodeQA' dataset is used to evaluate the ability of models to understand and reason about long code snippets in software engineering tasks.

Papers using LongCodeQA (3)

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents2026 · 1 citesFastCode: Fast and Cost-Efficient Code Understanding and Reasoning2026LongCodeBench: Evaluating Coding LLMs at 1M Context Windows2025