Mistral launches Leanstral, an open-source code agent for Lean 4
Original: Leanstral: Open-Source foundation for trustworthy vibe-coding View original →
Mistral says Leanstral is the first open-source code agent designed specifically for Lean 4, the proof assistant used in formal verification and theorem proving. Announced on March 16, 2026, the model is presented as infrastructure for trustworthy vibe-coding rather than a general assistant retrofitted to formal methods after the fact.
The company’s pitch is centered on efficiency and repository realism. Mistral says Leanstral runs with 6B active parameters and was trained to operate in realistic formal repositories, not only on isolated contest-style math tasks. It also said it will publish a technical report and release FLTEval, a benchmark suite meant to evaluate formal reasoning beyond competition math.
- Purpose-built for Lean 4 workflows
- Released under an Apache 2.0 license
- Available inside Mistral Vibe and through the
labs-leanstral-2603API endpoint - Downloadable weights for self-hosted use
Mistral’s blog argues that Leanstral delivers better efficiency than much larger open-source peers on FLTEval. In the published comparison, the company says Leanstral reaches competitive scores with fewer passes and continues scaling as additional passes are allowed. That matters because formal methods tooling is usually constrained not just by raw capability, but by latency, compute cost, and the need to behave predictably inside structured repositories.
The broader significance is that formal verification is moving closer to mainstream developer tooling. By combining an open license, direct product integration, and a benchmark focused on real formal workloads, Mistral is signaling that verified code generation and proof-oriented programming are becoming a practical product category, not just a research demo. For teams working with theorem proving, protocol verification, or safety-critical software, Leanstral is a notable attempt to make that stack cheaper and easier to deploy.
Related Articles
OpenCode drew 1,238 points and 614 comments on Hacker News, highlighting an open-source AI coding agent that spans terminal, IDE, and desktop clients. The project site emphasizes broad provider support, LSP integration, multi-session workflows, and a privacy-first posture.
Together AI said on March 13, 2026 that v2 of Open Deep Research is fully free and open source. The companion blog describes a planner and self-reflection workflow for multi-hop web research and ships code plus evaluation assets for developers.
Alibaba Qwen team released the Qwen 3.5 small model series (0.8B to 9B). Models run in-browser via WebGPU and show dramatic benchmark improvements over previous generations.