Le Chonk: Built for Coders, Trusted by Defenders.

Mistral Large 4 (Le Chonk) is now open weight | Mistral

Mistral Large 4 (Le Chonk) Built for Coders, Trusted by Defenders.

Mistral Large 4 (Le Chonk) Built for Coders, Trusted by Defenders.

Back to Blog

Share this post

Copy url to clipboard Copied

Thinking Summary

Mistral released Mistral Large 4 (Le Chonk), a 1-trillion-parameter multimodal model, now available with improved coding, cybersecurity, and reasoning efficiency. It leads open-weight benchmarks in coding and defensive security while offering three reasoning modes for cost-performance balance. Fully open-weight and European-trained, it empowers sovereign AI with customizable, self-hosted deployment options.

We release the weights of Le Chonk, advancing the frontier of open models in agentic coding and cybersecurity. Earlier this month, we released Mistral Large 4 (Le Chonk), our flagship 1-trillion-parameter, natively multimodal model, in public preview. The response to the preview has exceeded our expectations, and we're grateful to our developer community, early-access customers, and partners for their support, collaboration, and feedback. Since then, we've put that feedback to work while continuing to scale reinforcement learning, driving massive improvements in coding and defensive cybersecurity . Gains continue to accelerate, with no signs of saturation. Today, we're releasing the weights of this improved Mistral Large 4. The new model also features substantial gains in reasoning efficiency that give developers greater performance while lowering inference costs. Mistral Large 4 ranks as the best open-weight model for coding and among the world's most capable open models overall. Trained from scratch on European infrastructure with clear lineage from inception to release, it gives organizations a trusted foundation for Sovereign AI Mistral is defining the sovereign AI category and leading the open frontier. We're committed to building the world's most capable models and releasing them openly, giving developers, enterprises, and institutions the power to own, customize, and control their AI. Built for the Builders. Mistral Large 4 entered public preview with strong results across leading coding benchmarks. Just three weeks of additional reinforcement learning have since propelled it to the forefront of open-weight coding, taking the lead on FrontierCode and Terminal-Bench while matching the best open-weight models on the Artificial Analysis Coding Agent Index with substantially greater token efficiency. On Cognition's private FrontierCode 2.0 benchmark, which assesses end-to-end code quality and whether a repository maintainer would merge the agent's change, Mistral Large 4 leads with a score of 19.7%. Cognition - FrontierCode 2.0

Download PNG Download SVG

0.0% 5.0% 10.0% 15.0% 20.0% 19.7% 2.9% 14.2% 17.3% 17.8% 19.3% Mistral Large 4 Beam 1.0 GLM-5.3 Flash Kimi K3 GLM-5.3 DeepSeek V4.1 Flash Score

Pushing the pareto frontier for agentic coding. Mistral Large 4 delivers frontier coding performance with significantly fewer tokens, making sophisticated coding agents more economical to run at scale. On the Artificial Analysis Coding Agent Index, Mistral Large 4 scores 48%, effectively tied with the leading open-weight model, GLM-5.3, while using 47% fewer tokens per task on average. Artificial Analysis Coding Agent Index vs. Token Efficiency

Download PNG Download SVG

Mistral

Other models

Sweet spot 20 30 40 50 0 2 4 6 8 10 12 14 16 18 20 Score Average Tokens per Task in millions Mistral Large 4 - Medium Mistral Large 4 - High Muse Spark Open - xhigh GLM-5.3 DeepSeek V4.1 Flash 1017 Kimi K3

Coding Agent Index scores and token efficiencies for reasoning levels available on Artificial Analysis The gains extend to terminal-based coding workflows. On Terminal-Bench 4.0, Mistral Large 4 improved by 13 percentage points to 41% compared to its public preview, taking the lead among open-weight models while reducing output tokens by 30%. Artificial Analysis Coding Agent Index - Terminal-Bench 4.0

Download PNG Download SVG

0% 10% 20% 30% 40% 50% 28% 41% 3% 6% 21% 31% 40% ML4 Preview - self reported Mistral Large 4 Beam 1.0 Muse Spark Open Kimi K3 DeepSeek V4.1 Flash 1017 GLM-5.3

To give developers greater control over this tradeoff between performance and cost, Mistral Large 4 now supports three reasoning modes: Mode Recommended Use

Low Simple tasks; replaces ‘None’ reasoning mode

Medium Everyday tasks

High (default) Hardest use cases requiring high precision and thorough reasoning

Beyond benchmarks, Mistral Large 4's coding capabilities are validated by human preference. In Surge Code's blind pairwise evaluations, Mistral Large 4 was preferred over leading open-weight models including GLM-5.3, Kimi K3, and DeepSeek V4.1 Flash, ranking behind only Claude Opus 5.5 among the models evaluated. Surge Code - Human preference on code Blind side-by-side win rates against other models

Download PNG Download SVG

Mistral Large 4 win

Other model

GLM-5.3 Kimi K3 DeepSeek V4.1 Flash Claude Opus 5.5 50% 64% 36% 64% 36% 56% 44% 22% 78%

Share of prompts where graders preferred Mistral Large 4's answer over the opponent's. Built for the Defenders. Since its preview, we've been working with leading cybersecurity vendors to evaluate Mistral Large 4 in real-world environments to test Mistral Large 4’s strengths in vulnerability reproduction and patching. Mistral Large 4 scores 51% on the Artificial Analysis Cyber Index, which measures a model’s ability to discover vulnerabilities in a codebase, reproduce and validate them, and patch them without breaking existing functionality. Crucially, Mistral Large 4 handles these legitimate defensive security tasks without unnecessary refusals. Artificial Analysis - Cyber Index

Download PNG Download SVG

0% 20% 40% 60% 51% 34% 36% 41% 50% 56% 57% Mistral Large 4 Beam 1.0 GLM-5.3 Kimi K3 GLM-5.3 Flash MiMo-V2.6-Pro DeepSeek-V4.1- Flash 1017

Safety has improved alongside capability. Our model’s built-in guardrails distinguishes between defensive and malicious, offensive cybersecurity tasks. It retains strong performance on Cyber benchmarks, while achieving an average refusal rate of 96.6% on malicious cyber requests, the highest we measure among open models. Refusal of harmful cyber requests

Download PNG Download SVG

40% 60% 80% 100% 95% 97% 51% 84% 87% 94% Mistral Large 4 Preview Mistral Large 4 DeepSeek-V4-Pro Gemma-4-31B GLM-5.3 Kimi K3

Average refusal on the cyber-related...