Mistral AI, proprietary

# Codestral

> Codestral by Mistral AI, released May 2024. Ranked #290 of 354 with a Noometry Index of 30.6. API: $0.30 in / $0.90 out per M tokens. 256K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/codestral
- Last updated: 2026-10-10
- Title: Codestral Benchmarks, Price & Rank (October 2026) | Noometry

Codestral by Mistral AI ranks 290th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.6. Its strongest category is reasoning, where it ranks 251st. API pricing starts at $0.30 per million input tokens and $0.90 per million output tokens, with a 256K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #290 of 354
- **Index score:** 30.6
- **Evidence:** Reported 7 results
- **Provider:** [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral)
- **Released:** May 29, 2024
- **Weights:** Proprietary
- **Reasoning:** No
- **Context window:** 256K
- **Max output:** 8K
- **Input price:** $0.30 / M
- **Output price:** $0.90 / M
- **Blended price:** $0.45 / M
- **Output speed:** 271 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #85 of 219
- **Knowledge cutoff:** October 2024
- **Input:** text

## Category scores

Each category score combines every public result we have in that category.

Codestral category scores

1.  Coding 27.3
2.  Reasoning 19.8
3.  182022242628

Codestral category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 27.3 | #321 | 3 |
| [Reasoning](https://noometry.com/best/reasoning) | 19.8 | #251 | 1 |

## Strengths and weaknesses

Categories where Codestral places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Codestral: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 19.8 | −3.9 | #251 of 350, top 72% |

### Weakest categories

Codestral: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 27.3 | −11.4 | #321 of 340, top 95% |

## Closest competitors

The models ranked just above and below Codestral. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Codestral
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Granite 3.0 2b Instruct](https://noometry.com/models/granite-3-0-2b-instruct) | #286 | 30.8 | — | — | [Compare](https://noometry.com/compare/codestral-vs-granite-3-0-2b-instruct) |
| [Codellama 34b Instruct](https://noometry.com/models/codellama-34b-instruct) | #287 | 30.8 | — | — | [Compare](https://noometry.com/compare/codellama-34b-instruct-vs-codestral) |
| [Llama 3.1-405B](https://noometry.com/models/llama-3-1-405b) | #288 | 30.7 | — | 78 | [Compare](https://noometry.com/compare/codestral-vs-llama-3-1-405b) |
| [Yi-1.5-34B](https://noometry.com/models/yi-1-5-34b) | #289 | 30.6 | — | — | [Compare](https://noometry.com/compare/codestral-vs-yi-1-5-34b) |
| [Llama-3.3-70B-Instruct](https://noometry.com/models/llama-3-3-70b-instruct) | #291 | 30.6 | $0.16 | — | [Compare](https://noometry.com/compare/codestral-vs-llama-3-3-70b-instruct) |
| [GPT-4 Turbo](https://noometry.com/models/gpt-4-turbo) | #292 | 30.5 | $15 | — | [Compare](https://noometry.com/compare/codestral-vs-gpt-4-turbo) |
| [Qwen1.5-32B](https://noometry.com/models/qwen1-5-32b) | #293 | 30.5 | — | — | [Compare](https://noometry.com/compare/codestral-vs-qwen1-5-32b) |
| [Amazon Nova Micro](https://noometry.com/models/amazon-nova-micro) | #294 | 30.4 | $0.0613 | — | [Compare](https://noometry.com/compare/amazon-nova-micro-vs-codestral) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Codestral Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 11.1% | #41 of 44, top 94% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 41.8% | #30 of 64, top 47% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-05-23 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 52.5% | #26 of 66, top 40% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-05-23 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 137.78 | #105 of 105, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 73.8% | #16 of 45, top 36% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 61.9% | #22 of 38, top 58% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Reasoning

Codestral Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 32.5% | #91 of 99, top 92% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |

## API pricing by provider

Codestral API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | $0.30 | $0.90 | — | 2026-10-10 |
| [mistral](https://docs.mistral.ai/getting-started/models/) | $0.30 | $0.90 | $0.03 | 2026-10-10 |
| [openrouter](https://openrouter.ai/mistralai/codestral-2508) | $0.30 | $0.90 | $0.03 | 2026-10-10 |

[All Mistral AI API prices →](https://noometry.com/llm-pricing/mistral) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Codestral

-   [Codestral vs Yi-1.5-34B](https://noometry.com/compare/codestral-vs-yi-1-5-34b)
-   [Codestral vs Llama-3.3-70B-Instruct](https://noometry.com/compare/codestral-vs-llama-3-3-70b-instruct)
-   [Codestral vs Llama 3.1-405B](https://noometry.com/compare/codestral-vs-llama-3-1-405b)
-   [Codestral vs GPT-4 Turbo](https://noometry.com/compare/codestral-vs-gpt-4-turbo)
-   [Codestral vs Codellama 34b Instruct](https://noometry.com/compare/codellama-34b-instruct-vs-codestral)
-   [Codestral vs Qwen1.5-32B](https://noometry.com/compare/codestral-vs-qwen1-5-32b)
-   [Codestral vs GPT-6 Astra](https://noometry.com/compare/codestral-vs-gpt-6-astra)
-   [Codestral vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-codestral)
-   [Codestral vs Gemini 3.8 Flash](https://noometry.com/compare/codestral-vs-gemini-3-8-flash)
-   [Codestral vs Kimi K3](https://noometry.com/compare/codestral-vs-kimi-k3)
-   [Codestral vs Grok 4.6](https://noometry.com/compare/codestral-vs-grok-4-6)
-   [Codestral vs Qwen3.8 Max](https://noometry.com/compare/codestral-vs-qwen3-8-max)
-   [Codestral vs GLM-5.3](https://noometry.com/compare/codestral-vs-glm-5-3)
-   [Codestral vs Muse Spark 1.3](https://noometry.com/compare/codestral-vs-muse-spark-1-3)

## Other Mistral AI models

-   [Mistral Large 4](https://noometry.com/models/mistral-large-4)43.1
-   [Mistral Medium 3.5](https://noometry.com/models/mistral-medium-3-5)40.2
-   [Mistral Large 3](https://noometry.com/models/mistral-large-3)39.1
-   [Mistral Medium](https://noometry.com/models/mistral-medium)36.3
-   [Magistral Medium](https://noometry.com/models/magistral-medium)35.2
-   [Devstral Small 2505](https://noometry.com/models/devstral-small)34.3
-   [Mistral Small](https://noometry.com/models/mistral-small)33.4
-   [Pixtral Large](https://noometry.com/models/pixtral-large)32.2

## Frequently asked questions

### How good is Codestral?

Codestral by Mistral AI ranks 290th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.6. Its strongest category is reasoning, where it ranks 251st. API pricing starts at $0.30 per million input tokens and $0.90 per million output tokens, with a 256K-token context window.

### How much does Codestral cost?

Codestral costs $0.30 per million input tokens and $0.90 per million output tokens on Mistral AI's own API, with cached input at $0.03.

### What is Codestral's context window?

Codestral accepts up to 256K tokens of input and can write up to 8K tokens in one response.

### Is Codestral open source?

No. Codestral is proprietary and available only through Mistral AI's API and partner platforms.

### How fast is Codestral?

Codestral generated about 271 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Codestral's strengths and weaknesses?

Relative to other ranked models, Codestral places best in reasoning and lowest in coding.

### What is Codestral best at?

Its best category is reasoning, where it ranks 251st on Noometry.

### Cite this page

Noometry. (2026). Codestral benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/codestral

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/codestral.md).