Introducing Mistral Small 4
Get smart on it
Mistral Small 4 is a new AI model that combines reasoning, coding, and image-understanding capabilities into a single system, rather than requiring users to switch between separate specialized models. The model uses a mixture of experts architecture with 119 billion total parameters, supports a 256k context window, and allows users to adjust reasoning effort dynamically depending on whether they need fast responses or deep analysis. It performs competitively with other large models while generating shorter outputs, which reduces latency and inference costs. The model is released under an open-source Apache 2.0 license and is available through multiple platforms and deployment options.
Related news
Vibe coding platform Base44 launches own model as AI startups seek defensibility
Wix-owned vibe coding platform Base44 has started rolling out its own AI model — with hopes that it will eventually outperform frontier models.
DiScoFormer: One transformer for density and score, across distributions
DiScoFormer is a transformer model that estimates both the density and score of a data distribution in a single forward pass without requiring retraining for new distributions. The density describes where data points cluster, while the score, the gradient of log-density, points toward more probable regions and is used in diffusion-based generative models, Bayesian sampling, and scientific simulations. Existing methods force a trade-off: classical kernel density estimation works on any distribution but loses accuracy in high dimensions, while neural score-matching models stay accurate in high dimensions but must be retrained for each new distribution. DiScoFormer significantly outperforms kernel density estimation, cutting score error by 6.5 times and density error by more than 37 times in 100 dimensions, while generalizing to distributions with shapes and complexities not seen during training.
