# Codestral Review & Benchmarks (2026): Price, Context, Specs | Alher Tech

> Codestral by Mistral AI: benchmarks, pricing, context window, strengths and use cases. Data from official benchmark sources.

- Canonical page: https://alhertech.com/en/ai-comparison/codestral/
- Site: Alher Tech (custom software, AI agents and SEO engineering, https://alhertech.com/)
- Contact: https://alhertech.com/en/contact/

---

Last updated: April 22, 2026

## Specs

- **Vendor**: Mistral AI
- **Released**: January 13, 2025
- **Context window**: 256K tokens
- **Input**: $0.3 / M tokens
- **Output**: $0.9 / M tokens

## Benchmarks

- **mmlu**: 73.2
- **gpqa**: 41
- **humanEval**: 89.7
- **arenaElo**: 1254
- **sweBench**: 35
- **sweBenchPro**: 26
- **liveCodeBench**: 55
- **aiderPolyglot**: 51
- **terminalBench**: 18
- **mmluPro**: 50
- **hle**: 3
- **aime**: 30
- **math500**: 65

## Strengths

- Purpose-built for coding, strong HumanEval for its price
- Supports 80+ programming languages
- FIM (fill-in-the-middle) for IDE use cases

## Weaknesses

- Weak outside code tasks (low GPQA)
- No vision or agentic capabilities
- Not the best for code review reasoning

## Best for

- Custom IDE autocomplete and inline suggestions
- Low-latency coding copilots
- Code translation and refactoring

[Compare with other AI models](https://alhertech.com/en/ai-comparison/)