# Codestral vs Qwen3.5 397B-A17B

> Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 30.6 on the Noometry Index. Codestral costs 3.0× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-qwen3-5-397b-a17b
- Last updated: 2026-10-12
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Qwen3.5 397B-A17B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 34.5 to 19.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 73.7% for Qwen3.5 397B-A17B.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 256K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.6 | 46.0 |
| Rank | 290 | 67 |
| Context | 256K | 262K |
| Input $/M | $0.30 | $0.60 |
| Output $/M | $0.90 | $3.60 |
| Weights | Proprietary | Open |

## Coding

- Codestral: 27.3 (#321)
- Qwen3.5 397B-A17B: 42.0 (#114)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1465 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Qwen3.5 397B-A17B: 33.3 (#53)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |

## Reasoning

- Codestral: 19.8 (#251)
- Qwen3.5 397B-A17B: 34.5 (#70)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |

## Math

- Codestral: —
- Qwen3.5 397B-A17B: 46.1 (#73)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LMArena Math | — | 1454 |

## Knowledge

- Codestral: —
- Qwen3.5 397B-A17B: 53.3 (#58)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | — | 86.4% |
| LMArena Expert | — | 1462 |

## Multimodal

- Codestral: —
- Qwen3.5 397B-A17B: 40.7 (#44)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |

## Multilingual

- Codestral: —
- Qwen3.5 397B-A17B: 53.7 (#59)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1500 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1441 |

## Instruction Following

- Codestral: —
- Qwen3.5 397B-A17B: 75.0 (#77)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | — | 1424 |

## Long Context

- Codestral: —
- Qwen3.5 397B-A17B: 44.1 (#74)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | — | 1442 |

## Writing & Preference

- Codestral: —
- Qwen3.5 397B-A17B: 62.3 (#79)

| Benchmark | Codestral | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | — | 1438 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1446 |

## FAQ

### Is Codestral better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 30.6 on the Noometry Index. Codestral costs 3.0× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.

### Which is cheaper, Codestral or Qwen3.5 397B-A17B?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.

### Is Codestral or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5 397B-A17B does, with 262K tokens against 256K.

### How many benchmarks do Codestral and Qwen3.5 397B-A17B share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Qwen3.5 397B-A17B has 36.