# Gemma 3n E4b IT vs Sonar

> Sonar is the stronger model overall, scoring 37.8 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 13× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3n-e4b-it-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in instruction following, where Sonar leads 71.5 to 66.3.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $1 / $1 for Sonar.
- Sonar accepts more context: 128K tokens versus 33K.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3n E4b IT | Sonar |
|---|---|---|
| Provider | Google | Perplexity |
| Noometry Index | 36.7 | 37.8 |
| Rank | 203 | 184 |
| Context | 33K | 128K |
| Input $/M | $0.06 | $1 |
| Output $/M | $0.12 | $1 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3n E4b IT: 36.4 (#193)
- Sonar: 35.1 (#217)

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1269 | — |

## Reasoning

- Gemma 3n E4b IT: 19.2 (#239)
- Sonar: 20.3 (#221)

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1284 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- Gemma 3n E4b IT: 32.5 (#186)
- Sonar: 31.3 (#197)

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1251 | — |

## Knowledge

- Gemma 3n E4b IT: 33.6 (#193)
- Sonar: —

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LMArena Expert | 1245 | — |

## Multilingual

- Gemma 3n E4b IT: 43.5 (#179)
- Sonar: —

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LMArena Non-English | 1285 | — |
| LMArena Chinese | 1310 | — |
| LMArena French | 1330 | — |
| LMArena German | 1312 | — |
| LMArena Japanese | 1274 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1288 | — |
| LMArena Spanish | 1305 | — |

## Instruction Following

- Gemma 3n E4b IT: 66.3 (#205)
- Sonar: 71.5 (#146)

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1255 | — |

## Long Context

- Gemma 3n E4b IT: 38.8 (#185)
- Sonar: —

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LMArena Longer Query | 1277 | — |

## Writing & Preference

- Gemma 3n E4b IT: 50.3 (#181)
- Sonar: 52.6 (#166)

| Benchmark | Gemma 3n E4b IT | Sonar |
|---|---|---|
| LMArena Text | 1306 | — |
| LMArena Creative Writing | 1287 | — |
| LMArena Multi-Turn | 1276 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Gemma 3n E4b IT better than Sonar?

Sonar is the stronger model overall, scoring 37.8 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 13× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3n E4b IT or Sonar?

Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Sonar lists at $1 and $1.

### Is Gemma 3n E4b IT or Sonar better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Sonar does, with 128K tokens against 33K.

### How many benchmarks do Gemma 3n E4b IT and Sonar share?

0 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Sonar has 7.