{"slug": "jetbrains-mellum-2-1-open-coding-agent-model-explained", "title": "JetBrains Mellum 2.1: Open Coding Agent Model Explained", "summary": "JetBrains released Mellum 2.1, an open coding-agent model whose SWE-bench score rose from 2% to 47% through reinforcement learning alone, with no architecture changes, according to byteiota. The report covers the model's benchmarks, deployment commands, and where it fits in an agent stack.", "body_md": "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.\n\nThe post \nJetBrains Mellum 2.1: Open Coding Agent Model Explained\n appeared first on \nbyteiota\n.", "url": "https://wpnews.pro/news/jetbrains-mellum-2-1-open-coding-agent-model-explained", "canonical_source": "https://byteiota.com/jetbrains-mellum-2-1-coding-agent-model/", "published_at": "2026-10-20 08:09:18+00:00", "updated_at": "2026-10-20 08:17:18.473358+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-tools", "developer-tools", "ai-research"], "entities": ["JetBrains", "Mellum 2.1", "SWE-bench", "byteiota"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/jetbrains-mellum-2-1-open-coding-agent-model-explained", "markdown": "https://wpnews.pro/news/jetbrains-mellum-2-1-open-coding-agent-model-explained.md", "text": "https://wpnews.pro/news/jetbrains-mellum-2-1-open-coding-agent-model-explained.txt", "jsonld": "https://wpnews.pro/news/jetbrains-mellum-2-1-open-coding-agent-model-explained.jsonld"}}