# Granite 4.2 30b vs Sonar

> Granite 4.2 30b is the stronger model overall, scoring 41.8 to 38.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-30b-vs-sonar
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Granite 4.2 30b leads 27.8 to 21.1.
- Granite 4.2 30b has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 4.2 30b | Sonar |
|---|---|---|
| Provider | IBM | Perplexity |
| Noometry Index | 41.8 | 38.5 |
| Rank | 130 | 187 |
| Context | — | 128K |
| Input $/M | — | $1 |
| Output $/M | — | $1 |
| Weights | Open | Proprietary |

## Coding

- Granite 4.2 30b: 41.0 (#126)
- Sonar: 35.7 (#221)

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1396 | — |

## Reasoning

- Granite 4.2 30b: 27.8 (#112)
- Sonar: 21.1 (#227)

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1374 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- Granite 4.2 30b: —
- Sonar: 33.7 (#200)

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |

## Knowledge

- Granite 4.2 30b: 39.1 (#138)
- Sonar: —

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LMArena Expert | 1406 | — |

## Multilingual

- Granite 4.2 30b: 47.3 (#151)
- Sonar: —

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LMArena Non-English | 1340 | — |
| LMArena Chinese | 1414 | — |
| LMArena Russian | 1343 | — |

## Instruction Following

- Granite 4.2 30b: 71.2 (#155)
- Sonar: 71.4 (#150)

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1347 | — |

## Long Context

- Granite 4.2 30b: 41.4 (#140)
- Sonar: —

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LMArena Longer Query | 1359 | — |

## Writing & Preference

- Granite 4.2 30b: 53.8 (#156)
- Sonar: 52.6 (#167)

| Benchmark | Granite 4.2 30b | Sonar |
|---|---|---|
| LMArena Text | 1361 | — |
| LMArena Creative Writing | 1288 | — |
| LMArena Multi-Turn | 1339 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Granite 4.2 30b better than Sonar?

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 38.5 on the Noometry Index.

### Is Granite 4.2 30b or Sonar better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 35.7 in the Noometry coding category.

### How many benchmarks do Granite 4.2 30b and Sonar share?

0 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Sonar has 7.