# Magistral Medium vs Qwen2.5-Coder-32B

> Magistral Medium is the stronger model overall, scoring 34.8 to 32.9 on the Noometry Index. Qwen2.5-Coder-32B costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Magistral Medium leads 38.6 to 22.4.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 128K tokens versus 33K.

## Snapshot

| | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 32.9 |
| Rank | 224 | 239 |
| Context | 128K | 33K |
| Input $/M | $2 | $0.66 |
| Output $/M | $5 | $1 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1319 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1251 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.41 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1249 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1222 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen2.5-Coder-32B: 38.0 (#230)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1232 | 1205 |
| LMArena Chinese | 1225 | 1222 |
| LMArena Russian | 1224 | 1228 |
| LMArena French | 1268 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1176 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1269 | — |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Qwen2.5-Coder-32B: 61.6 (#240)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen2.5-Coder-32B: 37.9 (#204)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1295 | 1251 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen2.5-Coder-32B: 41.8 (#235)

| Benchmark | Magistral Medium | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1255 | 1230 |
| LMArena Creative Writing | 1245 | 1174 |
| LMArena Multi-Turn | 1275 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Magistral Medium better than Qwen2.5-Coder-32B?

Magistral Medium is the stronger model overall, scoring 34.8 to 32.9 on the Noometry Index. Qwen2.5-Coder-32B costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.

### Which is cheaper, Magistral Medium or Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Magistral Medium lists at $2 and $5.

### Is Magistral Medium or Qwen2.5-Coder-32B better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 22.4 in the Noometry coding category.

### Which has the bigger context window?

Magistral Medium does, with 128K tokens against 33K.

### How many benchmarks do Magistral Medium and Qwen2.5-Coder-32B share?

12 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2.5-Coder-32B has 31.