# Magistral Medium vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.1 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-qwen2-5-max
- 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 Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2.5-Max leads 24.6 to 8.7.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.8 | 40.1 |
| Rank | 224 | 142 |
| Context | 128K | — |
| Input $/M | $2 | — |
| Output $/M | $5 | — |
| Weights | Open | Proprietary |

## Coding

- Magistral Medium: 38.6 (#161)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1319 | 1359 |
| SciCode | 39.2% | — |
| LiveBench Coding | — | 64.4% |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1360 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.54 |
| LiveBench | — | 62.3% |

## Math

- Magistral Medium: 32.4 (#187)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1249 | 1369 |
| LiveBench Math | — | 58.4% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1222 | 1337 |
| Confabulations | — | 21.8% |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1232 | 1352 |
| LMArena Chinese | 1225 | 1382 |
| LMArena French | 1268 | 1396 |
| LMArena German | 1248 | 1350 |
| LMArena Japanese | 1176 | 1299 |
| LMArena Korean | 1125 | 1304 |
| LMArena Russian | 1224 | 1353 |
| LMArena Spanish | 1269 | 1377 |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1254 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- Magistral Medium: 39.3 (#178)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1295 | 1358 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | Magistral Medium | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1255 | 1367 |
| LMArena Creative Writing | 1245 | 1339 |
| LMArena Multi-Turn | 1275 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |

## FAQ

### Is Magistral Medium better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 34.8 on the Noometry Index.

### Is Magistral Medium or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 38.6 in the Noometry coding category.

### How many benchmarks do Magistral Medium and Qwen2.5-Max share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Qwen2.5-Max has 27.