From the source
Mistral released Mistral Large 4, also called Le Chonk, an open-weight multimodal Mixture-of-Experts model that takes text and images as input and generates text.
- The model has about 1T total and 49B active parameters with a 1M-token context window, and is distributed under the Mistral Ecosystem Open-Weight License, an MIT derivative that limits model-as-a-service offerings.
- Mistral positions it for defensive security work, where vulnerability research and incident response can look like attacks and closed-source filters may block them, and says open weights put both the usage policy and the deployment under the user's control.
- Mistral Large 4 scores 82% on the Artificial Analysis Cyber Index test that asks a model to reproduce a real vulnerability in open-source software and then patch it, a score Mistral says is the highest reported on that test.
- On cyber prompts from JailbreakBench, StrongREJECT and AgentHarm, its average refusal rate is higher than any other open-weight model, according to Mistral.
- The text decoder has 72 layers, a hidden dimension of 6,144 and 64 attention heads, combining Multi-head Latent Attention with a
DeepSeek Sparse Attention indexer that selects up to 2,048 key positions per query, plus a 1.6B Pixtral vision encoder.
