# Codestral vs Qwen Plus

> Qwen Plus is the stronger model overall, scoring 37.1 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-qwen-plus
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Qwen Plus in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen Plus leads 38.9 to 27.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 63.3% for Qwen Plus.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 256K.

## Snapshot

| | Codestral | Qwen Plus |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 37.1 |
| Rank | 290 | 210 |
| Context | 256K | 1M |
| Input $/M | $0.30 | $0.40 |
| Output $/M | $0.90 | $1.20 |
| Weights | Proprietary | Proprietary |

## Coding

- Codestral: 27.3 (#321)
- Qwen Plus: 38.9 (#167)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1328 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.8 (#251)
- Qwen Plus: 28.4 (#107)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 63.3% |
| LMArena Hard Prompts | — | 1317 |
| DTBench | — | 81.1% |
| LMCA | — | 24% |

## Math

- Codestral: —
- Qwen Plus: 23.3 (#271)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| LMArena Math | — | 1326 |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Codestral: —
- Qwen Plus: 27.4 (#251)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| GPQA Diamond | — | 48.1% |
| LMArena Expert | — | 1328 |

## Multilingual

- Codestral: —
- Qwen Plus: 45.1 (#175)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| LMArena Non-English | — | 1310 |
| LMArena Chinese | — | 1347 |
| LMArena Japanese | — | 1251 |
| LMArena Russian | — | 1323 |

## Instruction Following

- Codestral: —
- Qwen Plus: 68.8 (#181)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | — | 1303 |

## Long Context

- Codestral: —
- Qwen Plus: 40.3 (#158)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| LMArena Longer Query | — | 1324 |

## Writing & Preference

- Codestral: —
- Qwen Plus: 52.2 (#176)

| Benchmark | Codestral | Qwen Plus |
|---|---|---|
| LMArena Text | — | 1326 |
| LMArena Creative Writing | — | 1293 |
| LMArena Multi-Turn | — | 1336 |

## FAQ

### Is Codestral better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 37.1 to 30.6 on the Noometry Index.

### Which is cheaper, Codestral or Qwen Plus?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen Plus lists at $0.40 and $1.20.

### Is Codestral or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.9 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

Qwen Plus does, with 1M tokens against 256K.

### How many benchmarks do Codestral and Qwen Plus share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Qwen Plus has 20.