Mistral released Leanstral-1.5-119B-A6B
Evolving story · 2 updatesLeanstral 1.5 AI ModelTimeline →Mistral has released Leanstral-1.5-119B-A6B, a free Apache-2.0 licensed model with 6B active parameters, showing significant performance upgrades in formal verification. It achieves state-of-the-art results on several benchmarks, including FATE-H and FATE-X.
- Leanstral 1.5 achieves state-of-the-art results on FATE-H and FATE-X benchmarks
- The model solves 587 out of 672 PutnamBench problems
- It is trained through mid-training, supervised fine-tuning, and reinforcement learning with CISPO
- Leanstral 1.5 is released under the Apache-2.0 license, making it free and open-source
The Leanstral 1.5 model is a notable upgrade, trained through a combination of mid-training, supervised fine-tuning, and reinforcement learning with CISPO. This approach enables the model to excel in agentic proof engineering.
The model's performance is demonstrated through its achievements on various benchmarks. For instance, it solves 587 out of 672 PutnamBench problems and achieves state-of-the-art results on FATE-H with 87% and FATE-X with 34%. These results underscore the model's capabilities in formal verification.
The release of Leanstral 1.5 is significant, given its free and open-source nature under the Apache-2.0 license. This makes it accessible to a wide range of developers and researchers, potentially accelerating advancements in AI and related fields.
The model's architecture and training methodology are designed to improve its performance in specific areas. By leveraging reinforcement learning with CISPO, the model can learn from its interactions and adapt to complex problem-solving tasks, particularly in formal verification and proof engineering.
offers a powerful tool for formal verification and proof engineering
advances the field of AI with significant performance upgrades
- CISPO
- a reinforcement learning framework
- PutnamBench
- a benchmark for formal verification problems
- FATE-H and FATE-X
- benchmarks for evaluating AI model performance
Cloud-Based Artificial Intelligence Classification of Common Intracranial Tumors on Magnetic Resonance Imaging - Cureus
Improving the matrix multiplication exponent with modern optimization and AlphaEvolve
AutoSR: Automatic Symbolic Regression by Searching Research States
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
Duke partners with Anthropic, offering “pay-as-you-go” Claude subscriptions - The Duke Chronicle
Duke University now offers students and faculty a pay-as-you-go subscription to Anthropic's Claude AI models, expanding access to cutting-edge AI tools.
Edgerunner AI CEO Tyler Saltsman on developing military artificial intelligence - foxbusiness.com
Edgerunner AI's CEO Tyler Saltsman explains the company's approach to developing artificial intelligence for military applications.
AI ToolsInside the Tokenizer: Why the Same Prompt Costs Different Amounts on Every Model
Different LLMs tokenize the same text into varying numbers of tokens, directly affecting API costs.
AI ToolsCOSP: The Prompting Trick Where Your LLM Grades Its Own Homework
A developer introduces COSP, a prompting technique that lets large language models evaluate their own responses for accuracy and quality.
Introducing ChatGPT for Teens: Built for learning, backed by protections
OpenAI has released a dedicated ChatGPT version for teens, featuring enhanced safety controls and learning-focused tools to encourage responsible AI use.
BusinessChatGPT is getting a dedicated mode for teens
OpenAI introduces a dedicated ChatGPT mode for teenagers, featuring enhanced safeguards and parental controls to address concerns about AI use by minors.