# JetBrains Mellum 2.1: Open Coding Agent Model Explained > Source: > Published: 2026-10-20 08:09:18+00:00 JetBrains Mellum 2.1 jumped from 2% to 47% on SWE-bench using RL alone — no architecture changes. Here is the breakdown, benchmarks, deployment commands, and where it slots into an agent stack. The post JetBrains Mellum 2.1: Open Coding Agent Model Explained appeared first on byteiota .