# MiMo-V2-Pro vs Sonar

> MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 38.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-pro-vs-sonar
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 52.6.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1 / $1 for Sonar.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | MiMo-V2-Pro | Sonar |
|---|---|---|
| Provider | Xiaomi | Perplexity |
| Noometry Index | 43.0 | 38.5 |
| Rank | 103 | 187 |
| Context | 1.05M | 128K |
| Input $/M | $0.43 | $1 |
| Output $/M | $0.87 | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- MiMo-V2-Pro: 43.8 (#83)
- Sonar: 35.7 (#221)

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| LMArena WebDev | 1433 | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1476 | — |
| ALE-Bench | 785.17 | — |

## Reasoning

- MiMo-V2-Pro: 22.1 (#206)
- Sonar: 21.1 (#227)

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| NYT Connections (extended) | 25.8% | — |
| Thematic Generalization | 45.9% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1457 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- MiMo-V2-Pro: 39.5 (#102)
- Sonar: 33.7 (#200)

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1447 | — |

## Knowledge

- MiMo-V2-Pro: 41.4 (#111)
- Sonar: —

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| LMArena Expert | 1478 | — |

## Multilingual

- MiMo-V2-Pro: 52.7 (#81)
- Sonar: —

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| LMArena Non-English | 1416 | — |
| LMArena Chinese | 1456 | — |
| LMArena French | 1469 | — |
| LMArena German | 1417 | — |
| LMArena Japanese | 1366 | — |
| LMArena Korean | 1400 | — |
| LMArena Russian | 1427 | — |
| LMArena Spanish | 1457 | — |

## Instruction Following

- MiMo-V2-Pro: 76.0 (#49)
- Sonar: 71.4 (#150)

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1445 | — |

## Long Context

- MiMo-V2-Pro: 41.5 (#138)
- Sonar: —

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
| LMArena Longer Query | 1455 | — |

## Writing & Preference

- MiMo-V2-Pro: 62.8 (#70)
- Sonar: 52.6 (#167)

| Benchmark | MiMo-V2-Pro | Sonar |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1415 | — |
| LMArena Multi-Turn | 1456 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is MiMo-V2-Pro better than Sonar?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 38.5 on the Noometry Index.

### Which is cheaper, MiMo-V2-Pro or Sonar?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Sonar lists at $1 and $1.

### Is MiMo-V2-Pro or Sonar better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 128K.

### How many benchmarks do MiMo-V2-Pro and Sonar share?

0 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Sonar has 7.