Mistral: Codestral 2508
● Excellent8.4
/ 10
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
Specifications
| Attribute | Value |
|---|---|
| Lab | Mistral AI |
| Tags | Coding |
| Overall Score | 8.4/10 |
| Release Date | 2025-08 |
| Context Window | 256,000 tokens |
| Input Price / 1M | $0.30 |
| Output Price / 1M | $0.90 |
| Input Modalities | Text, File |
| Output Modalities | Text |
Strengths
- Specialized for coding with fill-in-the-middle (FIM) support
- Low-latency design for high-frequency coding tasks
- Strong at code correction and test generation
- 256K context window for large codebase understanding
- Mistral-grade quality at competitive pricing ($0.30/$0.90)
Weaknesses
- Coding-specialized: weaker on general reasoning and creative tasks
- Not a general-purpose chat model
- Less suited for non-coding use cases
Best For
- Code completion and fill-in-the-middle workflows
- Automated test generation
- Code review and correction
- IDE integration for developer tooling
Sources & Further Reading
Related Models
Scores are aggregated from public benchmarks (MMLU, HumanEval, MATH, GSM8K, LMSYS) and normalized to a 1–10 scale. Methodology →