SWE-Bench

SWE-Bench is a standardized benchmark for evaluating large language models on real-world software engineering tasks. It measures an AI’s ability to resolve GitHub issues by generating correct code patches, with Anthropic’s Claude Opus 4.7 scoring 82.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.