# Codestral vs Qwen3.5-9B

> Qwen3.5-9B is the stronger model overall, scoring 33.3 to 30.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-qwen3-5-9b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Qwen3.5-9B leads 35.3 to 26.9.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Qwen3.5-9B accepts more context: 262K tokens versus 256K.

## Snapshot

| | Codestral | Qwen3.5-9B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.1 | 33.3 |
| Rank | 287 | 235 |
| Context | 256K | 262K |
| Input $/M | $0.30 | $0.10 |
| Output $/M | $0.90 | $0.15 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- Qwen3.5-9B: 35.3 (#213)

| Benchmark | Codestral | Qwen3.5-9B |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| SciCode | — | 27.5% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Qwen3.5-9B: 14.4 (#143)

| Benchmark | Codestral | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |

## Reasoning

- Codestral: 19.1 (#244)
- Qwen3.5-9B: 22.5 (#178)

| Benchmark | Codestral | Qwen3.5-9B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 12% |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
| Epoch Capabilities Index | — | 139.45 |

## Math

- Codestral: —
- Qwen3.5-9B: 33.5 (#174)

| Benchmark | Codestral | Qwen3.5-9B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 48.5% |
| OTIS Mock AIME 2024-2025 | — | 61.7% |

## Knowledge

- Codestral: —
- Qwen3.5-9B: 46.0 (#77)

| Benchmark | Codestral | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | — | 79% |

## FAQ

### Is Codestral better than Qwen3.5-9B?

Qwen3.5-9B is the stronger model overall, scoring 33.3 to 30.1 on the Noometry Index.

### Which is cheaper, Codestral or Qwen3.5-9B?

Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; Codestral lists at $0.30 and $0.90.

### Is Codestral or Qwen3.5-9B better for coding?

Qwen3.5-9B scores higher on coding benchmarks: 35.3 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 256K.

### How many benchmarks do Codestral and Qwen3.5-9B share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3.5-9B has 10.