Skip to content
← Models
Open weightsMistral AI/10 trustVerified
Leanstral 1.5 logo

Leanstral 1.5

Open 119B MoE prover for Lean 4: 587/672 PutnamBench, five real bugs found.

Visit official page →

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

Open weights

Released

July 2, 2026

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

theorem-provingformal-verificationmath-aicode-verification

Trust score — 8/10

/10 trustVerified

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.

Sources