# Magistral Medium vs Mistral Medium 3.5

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 1 category and Mistral Medium 3.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Medium 3.5 leads 52.1 to 39.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 41.4% for Mistral Medium 3.5.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 128K.

## Snapshot

| | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 34.8 | 39.6 |
| Rank | 224 | 151 |
| Context | 128K | 262K |
| Input $/M | $2 | $1.50 |
| Output $/M | $5 | $7.50 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1319 | 1461 |
| LMArena WebDev | — | 1263 |
| SciCode | 39.2% | — |

## Reasoning

- Magistral Medium: 8.7 (#342)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 41.4% |
| LMArena Hard Prompts | 1267 | 1436 |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 12.9% |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Epoch Capabilities Index | — | 141.42 |

## Math

- Magistral Medium: 32.4 (#187)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1249 | 1432 |

## Knowledge

- Magistral Medium: 32.9 (#199)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1222 | 1431 |

## Multimodal

- Magistral Medium: —
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Magistral Medium: 39.8 (#219)
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1232 | 1405 |
| LMArena Chinese | 1225 | 1443 |
| LMArena French | 1268 | 1448 |
| LMArena German | 1248 | 1453 |
| LMArena Korean | 1125 | 1387 |
| LMArena Russian | 1224 | 1396 |
| LMArena Spanish | 1269 | 1406 |
| LMArena Japanese | 1176 | — |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1414 |

## Long Context

- Magistral Medium: 39.3 (#178)
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1295 | 1414 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | Magistral Medium | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1255 | 1421 |
| LMArena Creative Writing | 1245 | 1372 |
| LMArena Multi-Turn | 1275 | 1423 |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is Magistral Medium better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 34.8 on the Noometry Index.

### Which is cheaper, Magistral Medium or Mistral Medium 3.5?

Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Magistral Medium or Mistral Medium 3.5 better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 128K.

### How many benchmarks do Magistral Medium and Mistral Medium 3.5 share?

17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mistral Medium 3.5 has 22.