
Leanstral 1.5
Open 119B MoE prover for Lean 4: 587/672 PutnamBench, five real bugs found.
About
Leanstral 1.5 is Mistral AI's open formal-verification model for the Lean 4 proof language, released July 2, 2026 under Apache 2.0. It is a 119B-parameter mixture-of-experts with 6B active parameters per token and a 256k context window.
Mistral reports it saturates miniF2F at 100%, solves 587 of 672 PutnamBench problems, and reaches state-of-the-art 87% on FATE-H and 34% on FATE-X, all at roughly $4 per problem versus an estimated $300+ for proprietary competitors.
Beyond math, it found five previously unknown bugs across 57 open-source repositories in a real-world code verification test. Weights are on Hugging Face with a free API endpoint.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 116; Trending score 82/100 from researcher assessment.