# MiMo-V2.5 vs Sonar

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 37.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.8 to 52.6.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1 / $1 for Sonar.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 128K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2.5 | Sonar |
|---|---|---|
| Provider | Xiaomi | Perplexity |
| Noometry Index | 43.0 | 37.8 |
| Rank | 89 | 184 |
| Context | 1.05M | 128K |
| Input $/M | $0.14 | $1 |
| Output $/M | $0.28 | $1 |
| Weights | Open | Proprietary |

## Coding

- MiMo-V2.5: 43.6 (#75)
- Sonar: 35.1 (#217)

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1469 | — |
| ALE-Bench | 513.95 | — |

## Reasoning

- MiMo-V2.5: 27.8 (#98)
- Sonar: 20.3 (#221)

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| CritPt | 3.7% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1450 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- MiMo-V2.5: 35.4 (#145)
- Sonar: 31.3 (#197)

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| ProofBench | 16% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1436 | — |

## Knowledge

- MiMo-V2.5: 40.2 (#109)
- Sonar: —

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Expert | 1459 | — |

## Multimodal

- MiMo-V2.5: 39.0 (#53)
- Sonar: —

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- MiMo-V2.5: 52.0 (#96)
- Sonar: —

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Non-English | 1404 | — |
| LMArena Chinese | 1467 | — |
| LMArena French | 1447 | — |
| LMArena German | 1421 | — |
| LMArena Japanese | 1304 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1395 | — |
| LMArena Spanish | 1412 | — |

## Instruction Following

- MiMo-V2.5: 75.7 (#55)
- Sonar: 71.5 (#146)

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1433 | — |

## Long Context

- MiMo-V2.5: 44.1 (#69)
- Sonar: —

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Longer Query | 1444 | — |

## Writing & Preference

- MiMo-V2.5: 61.8 (#82)
- Sonar: 52.6 (#166)

| Benchmark | MiMo-V2.5 | Sonar |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1392 | — |
| LMArena Multi-Turn | 1445 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is MiMo-V2.5 better than Sonar?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 37.8 on the Noometry Index.

### Which is cheaper, MiMo-V2.5 or Sonar?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Sonar lists at $1 and $1.

### Is MiMo-V2.5 or Sonar better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 128K.

### How many benchmarks do MiMo-V2.5 and Sonar share?

0 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Sonar has 7.