# Codestral vs Qwen3.5 122B-A10B

> Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 30.1 on the Noometry Index. Codestral costs 2.4× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-qwen3-5-122b-a10b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Qwen3.5 122B-A10B leads 38.8 to 26.9.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Qwen3.5 122B-A10B accepts more context: 262K tokens versus 256K.

## Snapshot

| | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.1 | 41.6 |
| Rank | 287 | 120 |
| Context | 256K | 262K |
| Input $/M | $0.30 | $0.40 |
| Output $/M | $0.90 | $3.20 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- Qwen3.5 122B-A10B: 38.8 (#155)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1436 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.1 (#244)
- Qwen3.5 122B-A10B: 26.4 (#121)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| LMArena Hard Prompts | — | 1421 |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |

## Math

- Codestral: —
- Qwen3.5 122B-A10B: 36.4 (#114)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | — | 1432 |

## Knowledge

- Codestral: —
- Qwen3.5 122B-A10B: 38.2 (#138)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | — | 11.2% |
| LMArena Expert | — | 1431 |

## Multimodal

- Codestral: —
- Qwen3.5 122B-A10B: 39.0 (#52)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Codestral: —
- Qwen3.5 122B-A10B: 51.8 (#101)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | — | 1400 |
| LMArena Chinese | — | 1462 |
| LMArena French | — | 1442 |
| LMArena German | — | 1425 |
| LMArena Japanese | — | 1364 |
| LMArena Korean | — | 1353 |
| LMArena Russian | — | 1400 |
| LMArena Spanish | — | 1423 |

## Instruction Following

- Codestral: —
- Qwen3.5 122B-A10B: 74.0 (#109)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | — | 1399 |

## Long Context

- Codestral: —
- Qwen3.5 122B-A10B: 43.0 (#105)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | — | 1410 |

## Writing & Preference

- Codestral: —
- Qwen3.5 122B-A10B: 60.2 (#98)

| Benchmark | Codestral | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | — | 1417 |
| LMArena Creative Writing | — | 1369 |
| LMArena Multi-Turn | — | 1416 |

## FAQ

### Is Codestral better than Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 30.1 on the Noometry Index. Codestral costs 2.4× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.

### Which is cheaper, Codestral or Qwen3.5 122B-A10B?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.

### Is Codestral or Qwen3.5 122B-A10B better for coding?

Qwen3.5 122B-A10B scores higher on coding benchmarks: 38.8 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5 122B-A10B does, with 262K tokens against 256K.

### How many benchmarks do Codestral and Qwen3.5 122B-A10B share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3.5 122B-A10B has 27.