# Gemma 2 27B vs Sonar

> Sonar is the stronger model overall, scoring 37.8 to 29.2 on the Noometry Index. Gemma 2 27B costs 1.5× 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-2-27b-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Sonar in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Sonar leads 31.3 to 10.0.
- The biggest single-benchmark swing is LiveBench Reasoning: 28.1% for Gemma 2 27B and 46.3% for Sonar.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $1 / $1 for Sonar.
- Sonar accepts more context: 128K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 27B | Sonar |
|---|---|---|
| Provider | Google | Perplexity |
| Noometry Index | 29.2 | 37.8 |
| Rank | 302 | 184 |
| Context | 8K | 128K |
| Input $/M | $0.65 | $1 |
| Output $/M | $0.65 | $1 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 27B: 33.5 (#243)
- Sonar: 35.1 (#217)

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LiveBench Coding | 36% | 35.1% |
| BigCodeBench Instruct | 42.8% | — |
| LMArena Coding | 1211 | — |
| BigCodeBench Complete | 52.5% | — |

## Reasoning

- Gemma 2 27B: 14.8 (#313)
- Sonar: 20.3 (#221)

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LiveBench Reasoning | 28.1% | 46.3% |
| LiveBench Data Analysis | 47.9% | 37.9% |
| LiveBench | 38.2% | 46.9% |
| LMArena Hard Prompts | 1199 | — |
| DTBench | 48% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.06 | — |

## Math

- Gemma 2 27B: 10.0 (#306)
- Sonar: 31.3 (#197)

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LiveBench Math | 26.5% | 41.6% |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LMArena Math | 1212 | — |
| MATH Level 5 | 27.9% | — |

## Knowledge

- Gemma 2 27B: 18.9 (#275)
- Sonar: —

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| LMArena Expert | 1172 | — |
| MMLU | 75.7% | — |

## Multilingual

- Gemma 2 27B: 38.8 (#221)
- Sonar: —

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LMArena Non-English | 1217 | — |
| LMArena Chinese | 1221 | — |
| LMArena French | 1246 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1228 | — |

## Instruction Following

- Gemma 2 27B: 60.7 (#244)
- Sonar: 71.5 (#146)

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LiveBench Instruction Following | 58.1% | 76.2% |
| LMArena Instruction Following | 1206 | — |

## Long Context

- Gemma 2 27B: 37.3 (#213)
- Sonar: —

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LMArena Longer Query | 1231 | — |

## Writing & Preference

- Gemma 2 27B: 44.4 (#220)
- Sonar: 52.6 (#166)

| Benchmark | Gemma 2 27B | Sonar |
|---|---|---|
| LiveBench Language | 32.6% | 44.1% |
| LMArena Text | 1231 | — |
| LMArena Creative Writing | 1241 | — |
| LMArena Multi-Turn | 1224 | — |

## FAQ

### Is Gemma 2 27B better than Sonar?

Sonar is the stronger model overall, scoring 37.8 to 29.2 on the Noometry Index. Gemma 2 27B costs 1.5× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.

### Which is cheaper, Gemma 2 27B or Sonar?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Sonar lists at $1 and $1.

### Is Gemma 2 27B or Sonar better for coding?

Sonar scores higher on coding benchmarks: 35.1 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Sonar does, with 128K tokens against 8K.

### How many benchmarks do Gemma 2 27B and Sonar share?

7 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Sonar has 7.