🔧 How a $0.02/Call Model Scored 78.2% on SWE-bench Verified — Beating Every Model on the Leaderboard

TL;DR


We added architectural context to AI coding agents via MCP and tested on SWE-bench Verified (500 real bugs). MiniMax M2.5 — a model that costs $0.02 per call — scored 78.2%, surpassing every model on the official mini-SWE-agent leaderboard, including Claude Opus 4.5 (76.8%) which costs 37x more per call. The improvement comes entirely from...