MathΣtral | Mistral AI

What this post added

Introduces MathΣtral, a specialized 7B parameter model derived from Mistral 7B, focusing on advanced mathematical problems requiring complex, multi-step logical reasoning. MathΣtral achieves state-of-the-art reasoning capacities in its size category across industry-standard benchmarks like MATH (56.6%) and MMLU (63.47%), demonstrating significant performance improvements over its base model in STEM subjects. It can achieve even better results with increased inference-time computation, such as 68.37% on MATH with majority voting and 74.59% with a strong reward model among 64 candidates. The model is released under an Apache 2.0 license and is available via HuggingFace, mistral-inference, and mistral-finetune.