# Codestral vs DeepSeek-V3.2-Speciale

> DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 30.6 on the Noometry Index. Codestral costs 1.9× less per token, which makes it the better buy when DeepSeek-V3.2-Speciale's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-deepseek-v3-2-speciale
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.9 to 19.8.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.58 / $1.68 for DeepSeek-V3.2-Speciale.
- Codestral accepts more context: 256K tokens versus 128K.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | DeepSeek-V3.2-Speciale |
|---|---|---|
| Provider | Mistral AI | DeepSeek |
| Noometry Index | 30.6 | 39.7 |
| Rank | 290 | 162 |
| Context | 256K | 128K |
| Input $/M | $0.30 | $0.58 |
| Output $/M | $0.90 | $1.68 |
| Weights | Proprietary | Open |

## Coding

- Codestral: 27.3 (#321)
- DeepSeek-V3.2-Speciale: 40.4 (#140)

| Benchmark | Codestral | DeepSeek-V3.2-Speciale |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| WeirdML | — | 46.7% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.8 (#251)
- DeepSeek-V3.2-Speciale: 32.9 (#73)

| Benchmark | Codestral | DeepSeek-V3.2-Speciale |
|---|---|---|
| SimpleBench | — | 52.6% |
| Kagi LLM Benchmark | 32.5% | — |

## Writing & Preference

- Codestral: —
- DeepSeek-V3.2-Speciale: 46.0 (#222)

| Benchmark | Codestral | DeepSeek-V3.2-Speciale |
|---|---|---|
| EQ-Bench Creative Writing | — | 1276 |

## FAQ

### Is Codestral better than DeepSeek-V3.2-Speciale?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 30.6 on the Noometry Index. Codestral costs 1.9× less per token, which makes it the better buy when DeepSeek-V3.2-Speciale's lead doesn't matter for your workload.

### Which is cheaper, Codestral or DeepSeek-V3.2-Speciale?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; DeepSeek-V3.2-Speciale lists at $0.58 and $1.68.

### Is Codestral or DeepSeek-V3.2-Speciale better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

Codestral does, with 256K tokens against 128K.

### How many benchmarks do Codestral and DeepSeek-V3.2-Speciale share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.