Model Cards / Mistral AI

Codestral Release

model card1,235 words·5 min read·Apr 17, 2026·Source
Summary

Codestral Release

A 355-word brief of a 1,235-word document. Published by Mistral AI. Version dated Apr 17, 2026.
01

What this is

Codestral is Mistral AI's first code-focused generative model, released May 29, 2024. It is a 22B open-weight model designed explicitly for code generation, completion, and interaction via a shared instruct and fill-in-the-middle API. It supersedes general-purpose Mistral models previously used for coding tasks.

02

Capabilities

Codestral is trained on 80+ programming languages, including Python, Java, C, C++, JavaScript, Bash, Swift, and Fortran. It supports a 32k context window, which Mistral contrasts with competitor windows of 4k, 8k, or 16k, and attributes its RepoBench lead to this advantage. On Kotlin-HumanEval at T=0.2, a JetBrains researcher reports Codestral scored 73.75, above GPT-4-Turbo at 72.05 and GPT-3.5-Turbo at 54.66. The model supports fill-in-the-middle (FIM) completion and is benchmarked against DeepSeek Coder 33B on FIM tasks across Python, JavaScript, and Java.

03

Evaluation methodology

Python ability is evaluated on HumanEval pass@1, MBPP sanitised pass@1, CruxEval (output prediction), and RepoBench EM (long-range repository-level completion). SQL performance is assessed using the Spider benchmark. Multilingual performance uses HumanEval pass@1 averaged across C++, Bash, Java, PHP, TypeScript, and C# in addition to Python. The document does not describe contamination controls or details of evaluation infrastructure.

04

Safety testing

The card does not discuss safety testing, red-teaming, or catastrophic-risk evaluations.

05

Mitigations

The card does not discuss content classifiers, refusal training, or safety mitigations. Access to the free beta endpoint is gated behind a waitlist, which Mistral describes as ensuring "a good quality of service" rather than as a safety control.

06

Deployment and access

Codestral is available for download on HuggingFace under the Mistral AI Non-Production License, permitting research and testing; commercial use requires a separate license obtained by contacting Mistral. A dedicated endpoint at codestral.mistral.ai is offered free during an 8-week beta period with waitlist gating and personal-level API keys not subject to organization rate limits. Standard token-billed access is also available at api.mistral.ai. Integrations are available in LlamaIndex, LangChain, Continue.dev, Tabnine, and Sourcegraph Cody, with self-deployment available through Mistral's enterprise offering.

07

Limitations

The card does not flag any limitations, failure modes, or unsolved problems identified by Mistral.

08

What's new

Codestral is Mistral AI's first code-specific model release and introduces a new dedicated API endpoint (codestral.mistral.ai). The document contains no version changelog or comparison to a prior Codestral release.

Generated by Claude sonnet from the cleaned source on Apr 23, 2026. Passages in double quotes are verbatim from the source; other text is neutral paraphrase. For citation, use the original: original document · source SHA 5863b0abc6d5.

Extracted Evaluations(3 results)

Sort by:3 evals
BenchmarkCategoryStateScoreVariantSource
HumanEvalcodingscored73.8T=0.2self-reported
HumanEvalcodingscored72.0T=0.2self-reported
HumanEvalcodingscored54.7T=0.2self-reported