Compare harnesses not models: Blitzy vs GPT-5.4 on SWE-Bench Pro

This blog post was authored by Piotr Migdal and Piotr Grabowski. Last year, agentic IDE tooling and vibe coding went mainstream. But enterprise systems – payments, mainframes, decade-old technology – aren’t disrupted by this. These codebases are enormous, require massive context, have very little public training data for the models to learn on, and are mission critical to the business. There is a massive untapped market here. For enterprise codebases, the model alone is not enough, placing a m...