# Magistral Medium vs Qwen3.5 Max Preview

> Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-qwen3-5-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Qwen3.5 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 29.6 to 8.7.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 44.7 |
| Rank | 224 | 72 |
| Context | 128K | — |
| Input $/M | $2 | — |
| Output $/M | $5 | — |
| Weights | Open | Proprietary |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen3.5 Max Preview: 43.4 (#79)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1319 | 1488 |
| SciCode | 39.2% | — |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen3.5 Max Preview: 29.6 (#81)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1483 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen3.5 Max Preview: 37.3 (#99)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1249 | 1473 |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen3.5 Max Preview: 41.1 (#104)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1222 | 1489 |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen3.5 Max Preview: 56.4 (#21)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1232 | 1465 |
| LMArena Chinese | 1225 | 1534 |
| LMArena French | 1268 | 1483 |
| LMArena German | 1248 | 1487 |
| LMArena Japanese | 1176 | 1497 |
| LMArena Korean | 1125 | 1438 |
| LMArena Russian | 1224 | 1472 |
| LMArena Spanish | 1269 | 1470 |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Qwen3.5 Max Preview: 77.2 (#28)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1254 | 1467 |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen3.5 Max Preview: 45.2 (#44)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1295 | 1477 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen3.5 Max Preview: 66.1 (#39)

| Benchmark | Magistral Medium | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1255 | 1471 |
| LMArena Creative Writing | 1245 | 1464 |
| LMArena Multi-Turn | 1275 | 1478 |

## FAQ

### Is Magistral Medium better than Qwen3.5 Max Preview?

Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 34.8 on the Noometry Index.

### Is Magistral Medium or Qwen3.5 Max Preview better for coding?

Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 38.6 in the Noometry coding category.

### How many benchmarks do Magistral Medium and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen3.5 Max Preview has 17.