# Amazon Nova Pro vs Gemma 2 27B

> Amazon Nova Pro is the stronger model overall, scoring 30.5 to 29.2 on the Noometry Index. Gemma 2 27B costs 2.2× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-gemma-2-27b
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Amazon Nova Pro scores higher in 7 categories and Gemma 2 27B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 26.4 to 10.0.
- The biggest single-benchmark swing is LiveBench Math: 38% for Amazon Nova Pro and 26.5% for Gemma 2 27B.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| Provider | Amazon | Google |
| Noometry Index | 30.5 | 29.2 |
| Rank | 278 | 302 |
| Context | 300K | 8K |
| Input $/M | $0.80 | $0.65 |
| Output $/M | $3.20 | $0.65 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- Gemma 2 27B: 33.5 (#243)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LiveBench Coding | 38.1% | 36% |
| LMArena Coding | 1270 | 1211 |
| BigCodeBench Instruct | — | 42.8% |
| BigCodeBench Complete | — | 52.5% |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- Gemma 2 27B: —

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- Gemma 2 27B: 14.8 (#313)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LiveBench Reasoning | 32.6% | 28.1% |
| LMArena Hard Prompts | 1246 | 1199 |
| LiveBench Data Analysis | 48.3% | 47.9% |
| Epoch Capabilities Index | 123.75 | 122.06 |
| LiveBench | 43.5% | 38.2% |
| DTBench | — | 48% |
| LMCA | — | 7.1% |

## Math

- Amazon Nova Pro: 26.4 (#240)
- Gemma 2 27B: 10.0 (#306)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LiveBench Math | 38% | 26.5% |
| LMArena Math | 1252 | 1212 |
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 27.9% |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- Gemma 2 27B: 18.9 (#275)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| Confabulations | 30.1% | 27.1% |
| LMArena Expert | 1211 | 1172 |
| MMLU | 82% | 75.7% |
| GPQA Diamond | — | 36.5% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |

## Multimodal

- Amazon Nova Pro: 24.5 (#121)
- Gemma 2 27B: —

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- Gemma 2 27B: 38.8 (#221)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1234 | 1217 |
| LMArena Chinese | 1244 | 1221 |
| LMArena French | 1270 | 1246 |
| LMArena German | 1243 | 1209 |
| LMArena Japanese | 1200 | 1175 |
| LMArena Korean | 1203 | 1174 |
| LMArena Russian | 1240 | 1234 |
| LMArena Spanish | 1182 | 1228 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- Gemma 2 27B: 60.7 (#244)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 58.1% |
| LMArena Instruction Following | 1235 | 1206 |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- Gemma 2 27B: 37.3 (#213)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1255 | 1231 |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- Gemma 2 27B: 44.4 (#220)

| Benchmark | Amazon Nova Pro | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1259 | 1231 |
| LMArena Creative Writing | 1212 | 1241 |
| LMArena Multi-Turn | 1245 | 1224 |
| LiveBench Language | 37% | 32.6% |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |

## FAQ

### Is Amazon Nova Pro better than Gemma 2 27B?

Amazon Nova Pro is the stronger model overall, scoring 30.5 to 29.2 on the Noometry Index. Gemma 2 27B costs 2.2× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Pro or Gemma 2 27B?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or Gemma 2 27B better for coding?

Amazon Nova Pro scores higher on coding benchmarks: 34.6 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 8K.

### How many benchmarks do Amazon Nova Pro and Gemma 2 27B share?

27 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemma 2 27B has 34.