# Mistral Large 4 vs Sonar

> Mistral Large 4 is the stronger model overall, scoring 43.1 to 38.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-4-vs-sonar
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Mistral Large 4 leads 48.6 to 35.7.
- Both cost about the same: $0.68 input and $2.09 output per million tokens.
- Mistral Large 4 accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Mistral Large 4 | Sonar |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 43.1 | 38.5 |
| Rank | 99 | 187 |
| Context | 1.05M | 128K |
| Input $/M | $0.68 | $1 |
| Output $/M | $2.09 | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- Mistral Large 4: 48.6 (#57)
- Sonar: 35.7 (#221)

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| LMArena WebDev | 1541 | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1475 | — |

## Reasoning

- Mistral Large 4: 22.5 (#192)
- Sonar: 21.1 (#227)

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| NYT Connections (extended) | 27.4% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1444 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- Mistral Large 4: 40.4 (#91)
- Sonar: 33.7 (#200)

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1488 | — |

## Knowledge

- Mistral Large 4: 36.6 (#166)
- Sonar: —

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| SimpleQA Verified | 20% | — |
| LMArena Expert | 1447 | — |

## Multilingual

- Mistral Large 4: 52.6 (#82)
- Sonar: —

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| LMArena Non-English | 1415 | — |
| LMArena Chinese | 1491 | — |
| LMArena Russian | 1414 | — |

## Instruction Following

- Mistral Large 4: 75.0 (#76)
- Sonar: 71.4 (#150)

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1424 | — |

## Long Context

- Mistral Large 4: 43.6 (#89)
- Sonar: —

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| LMArena Longer Query | 1429 | — |

## Writing & Preference

- Mistral Large 4: 60.4 (#97)
- Sonar: 52.6 (#167)

| Benchmark | Mistral Large 4 | Sonar |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1361 | — |
| LMArena Multi-Turn | 1424 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Mistral Large 4 better than Sonar?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 38.5 on the Noometry Index.

### Which is cheaper, Mistral Large 4 or Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.

### Is Mistral Large 4 or Sonar better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 128K.

### How many benchmarks do Mistral Large 4 and Sonar share?

0 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Sonar has 7.