# Magistral Medium vs Sonar

> Sonar is the stronger model overall, scoring 38.5 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Sonar leads 21.1 to 8.6.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Magistral Medium | Sonar |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 35.2 | 38.5 |
| Rank | 227 | 187 |
| Context | 262K | 128K |
| Input $/M | $2 | $1 |
| Output $/M | $5 | $1 |
| Weights | Open | Proprietary |

## Coding

- Magistral Medium: 39.1 (#161)
- Sonar: 35.7 (#221)

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| SciCode | 39.2% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1319 | — |

## Reasoning

- Magistral Medium: 8.6 (#348)
- Sonar: 21.1 (#227)

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1267 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- Magistral Medium: 35.1 (#189)
- Sonar: 33.7 (#200)

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1250 | — |

## Knowledge

- Magistral Medium: 33.5 (#202)
- Sonar: —

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Expert | 1223 | — |

## Multilingual

- Magistral Medium: 39.6 (#224)
- Sonar: —

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Non-English | 1232 | — |
| LMArena Chinese | 1227 | — |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Russian | 1224 | — |
| LMArena Spanish | 1271 | — |

## Instruction Following

- Magistral Medium: 66.0 (#211)
- Sonar: 71.4 (#150)

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1254 | — |

## Long Context

- Magistral Medium: 39.3 (#183)
- Sonar: —

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Longer Query | 1295 | — |

## Writing & Preference

- Magistral Medium: 46.3 (#219)
- Sonar: 52.6 (#167)

| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1245 | — |
| LMArena Multi-Turn | 1275 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Magistral Medium better than Sonar?

Sonar is the stronger model overall, scoring 38.5 to 35.2 on the Noometry Index.

### Which is cheaper, Magistral Medium or Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Magistral Medium lists at $2 and $5.

### Is Magistral Medium or Sonar better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

Magistral Medium does, with 262K tokens against 128K.

### How many benchmarks do Magistral Medium and Sonar share?

0 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Sonar has 7.