Mistral AI Launches Leanstral 1.5, an Open-Source Formal Verification Model

iconKuCoinFlash
Share
AI summary iconSummary
Mistral AI released Leanstral 1.5, an open-source formal verification model licensed under Apache-2.0. The model has 119 billion total parameters, with 6 billion active, achieving 100% saturation on miniF2F and solving 587 out of 672 problems on PutnamBench. It set new state-of-the-art records on FATE-H (87%) and FATE-X (34%). Trained using mid-training, supervised fine-tuning, and CISPO-based reinforcement learning, it exhibits agent-like proof capabilities and discovered five previously unknown bugs across 57 open-source repositories. The model is now available via Hugging Face and a free API. This AI + crypto news update highlights on-chain developments.
ME AI News: Mistral AI has released Leanstral 1.5, an open-source formal verification model under the Apache-2.0 license, with 119B total parameters but only 6B active. It achieves 100% saturation on miniF2F, solves 587 out of 672 problems on PutnamBench, and sets new SOTA scores on FATE-H (87%) and FATE-X (34%). The model was trained using mid-training, SFT, and reinforcement learning based on CISPO. It demonstrates agent-like proof capabilities and discovered 5 previously unknown bugs across 57 open-source repositories. The model is now available via Hugging Face and a free API. 🔗 Read the original: https://mistral.ai/news/leanstral-1-5 (Source: AiHot)
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information. Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.