Skip to content
AI News HubLIVE
More
Summary only

Leanstral 1.5: Proof Abundance for All

Leanstral 1.5, a free Apache-2.0 licensed model with 6B active parameters, delivers a major performance upgrade in formal verification, saturating miniF2F, solving 587/672 PutnamBench problems, and achieving state-of-the-art results on FATE-H (87%) and FATE-X (34%). Trained through mid-training, supervised fine-tuning, and reinforcement learning with CISPO, it excels in agentic proof engineering and real-world code verification, uncovering 5 previously unknown bugs across 57 repositories tested. Fully open-sourced and available via Hugging Face and a free API, Leanstral 1.5 is now accessible for practical proof engineering in Lean 4.

SourceHacker News AIAuthor: meetpateltech
Leanstral 1.5: Proof Abundance for All
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Leanstral 1.5 achieves near-perfect or state-of-the-art results on multiple formal math benchmarks, including 100% on miniF2F and 587/672 on PutnamBench.
  • It demonstrates strong code verification capabilities, proving AVL tree time complexity and discovering real-world bugs in open-source repositories.
  • The training uses a three-stage pipeline: mid-training, supervised fine-tuning, and reinforcement learning with CISPO, leveraging interactive and code agent environments.
  • The model is fully open-sourced under Apache-2.0 license, available via free API and Hugging Face.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models