Private enterprise code cuts coding-agent success below 40%
Public coding benchmarks can make agents look ready for the job. Real-SWE puts them inside licensed, private enterprise codebases, where tasks touch billing, taxes, customer migrations, and company-specific conventions; the top model-and-harness combination resolved only 38.8% of tasks. That makes context, integration, and business rules the bottleneck, not just code generation, and it is a tougher baseline for anyone deploying agents at work.