# Magistral Medium vs Qwen-14B

> Magistral Medium is the stronger model overall, scoring 34.8 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Magistral Medium scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Magistral Medium leads 46.5 to 27.8.

## Snapshot

| | Magistral Medium | Qwen-14B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 30.8 |
| Rank | 224 | 273 |
| Context | 128K | — |
| Input $/M | $2 | — |
| Output $/M | $5 | — |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen-14B: 30.6 (#283)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Coding | 1319 | 1072 |
| SciCode | 39.2% | — |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen-14B: 18.7 (#255)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1027 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen-14B: 28.7 (#224)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Math | 1249 | 1068 |
| GSM8K | — | 61.3% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen-14B: —

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Expert | 1222 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen-14B: 27.7 (#270)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1232 | 1042 |
| LMArena Chinese | 1225 | 1077 |
| 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)
- Qwen-14B: 52.6 (#284)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1031 |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen-14B: 31.3 (#276)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1295 | 1029 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen-14B: 27.8 (#294)

| Benchmark | Magistral Medium | Qwen-14B |
|---|---|---|
| LMArena Text | 1255 | 1051 |
| LMArena Creative Writing | 1245 | 1028 |
| LMArena Multi-Turn | 1275 | 1022 |

## FAQ

### Is Magistral Medium better than Qwen-14B?

Magistral Medium is the stronger model overall, scoring 34.8 to 30.8 on the Noometry Index.

### Is Magistral Medium or Qwen-14B better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 30.6 in the Noometry coding category.

### How many benchmarks do Magistral Medium and Qwen-14B share?

10 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen-14B has 18.