# Magistral Medium vs Qwen2.5 32B Instruct

> Magistral Medium is the stronger model overall, scoring 34.8 to 29.7 on the Noometry Index. Qwen2.5 32B Instruct costs 2.2× 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-qwen2-5-32b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Magistral Medium leads 32.4 to 15.3.
- Qwen2.5 32B Instruct is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Qwen2.5 32B Instruct accepts more context: 131K tokens versus 128K.

## Snapshot

| | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 29.7 |
| Rank | 224 | 291 |
| Context | 128K | 131K |
| Input $/M | $2 | $0.70 |
| Output $/M | $5 | $2.80 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen2.5 32B Instruct: 38.1 (#165)

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1319 | — |
| BigCodeBench Complete | — | 52.3% |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen2.5 32B Instruct: 18.5 (#262)

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1267 | — |
| Epoch Capabilities Index | — | 128.52 |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen2.5 32B Instruct: 15.3 (#289)

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| LMArena Math | 1249 | — |
| MATH Level 5 | — | 56.1% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen2.5 32B Instruct: 24.9 (#259)

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| LMArena Expert | 1222 | — |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen2.5 32B Instruct: —

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

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Qwen2.5 32B Instruct: —

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1254 | — |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen2.5 32B Instruct: —

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1295 | — |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen2.5 32B Instruct: —

| Benchmark | Magistral Medium | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1245 | — |
| LMArena Multi-Turn | 1275 | — |

## FAQ

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

Magistral Medium is the stronger model overall, scoring 34.8 to 29.7 on the Noometry Index. Qwen2.5 32B Instruct costs 2.2× 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 32B Instruct?

Qwen2.5 32B Instruct is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Magistral Medium lists at $2 and $5.

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

They score almost the same on coding (38.6 vs 38.1); test both on your own repository before choosing.

### Which has the bigger context window?

Qwen2.5 32B Instruct does, with 131K tokens against 128K.

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

0 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2.5 32B Instruct has 7.