Mistral Releases Leanstral 1.5, an Open Model That Solved 587 of 672 Putnam Math Problems
4 Articles
4 Articles
The French AI start-up Mistral AI has released Leantral 1.5, a new version of its specialized language model. It is intended to mathematically prove that programs fulfil certain characteristics, while also discovering errors that sometimes overlook classic software tests.
Mistral AI releases Leantral 1.5 under Apache 2.0 license. According to Mistral, the model solves 587 of 672 Putnam tasks and automatically finds bugs in code.
Mistral AI launches Leanstral 1.5, the free AI that checks the accuracy of your code, an open source Lean 4 code agent model capable of solving 587 of the 672 issues of the PutnamBenchMistral AI has launched Leanstral 1.5. It is a code agent model designed for Lean 4. This version is intended for automated demonstration of theorems and demonstration engineering. The weights are available under Apache 2.0 license. The architecture is of type "mix…
Mistral Releases Leanstral 1.5, an Open Model That Solved 587 of 672 Putnam Math Problems
Mistral AI has released Leanstral 1.5, an open-source model built to write and check formal proofs in Lean 4. It’s a specialized tool with a specific job: Verifying that mathematical reasoning and code logic are actually correct, not just plausible. The numbers are the headline. Mistral says the model hits 100% on miniF2F, a formal math benchmark that spans high school problems up through olympiad difficulty. On PutnamBench, a set of 672 problem…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium


