· 5 min read
ai
Devstral 2: Why Open-Source Just Won the Coding Agent War
Mistral's Devstral 2 achieves 72.2% on SWE-Bench at 7x cheaper than Claude Sonnet. Here's what this means for teams building AI-powered dev tooling in 2026.
Read moreIDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
3 articles
· 5 min read
ai
Mistral's Devstral 2 achieves 72.2% on SWE-Bench at 7x cheaper than Claude Sonnet. Here's what this means for teams building AI-powered dev tooling in 2026.
Read more· 6 min read
cost-optimization
Mistral Large 3's MoE architecture delivers 92% of GPT-5.2's performance at 15% of the cost. As a technical lead who has run open-source LLMs in production, here's where it works and where it fails.
Read more· 6 min read
ai
Mistral's Devstral 2 scores 72.2% on SWE-bench, ships under MIT license, and costs up to 7x less than Claude Sonnet. Here's how it works, when to use it, and whether open-source agentic coding is finally production-ready.
Read moreLooking for an article, exploring a product, or starting an AI project?