Model comparison
Amazon Nova Pro vs Gemma 3 27B
Amazon Nova Pro and Gemma 3 27B score almost the same on the Noometry Index (31.0 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Amazon Nova Pro scores higher in 5 categories and Gemma 3 27B in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Amazon Nova Pro leads 35.1 to 22.5.
- The biggest single-benchmark swing is Short-Story Creative Writing: 60.5% for Amazon Nova Pro and 79.9% for Gemma 3 27B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Gemma 3 27B | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 31.0 | 30.8 |
| Released | 2024-12-03 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 8K |
| Input $ / M tokens | $0.80 | $0.08 |
| Output $ / M tokens | $3.20 | $0.16 |
| Results tracked | 38 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Gemma 3 27B: 22.5 (#334)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LiveBench Coding | 38.1% | 39.9% |
| LMArena Coding | 1270 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
Agentic & Tool Use Gemma 3 27B leads
Amazon Nova Pro: 16.7 (#147), Gemma 3 27B: 25.1 (#110)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 29.5% |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Gemma 3 27B: 16.7 (#301)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LiveBench Reasoning | 32.6% | 43.8% |
| LMArena Hard Prompts | 1246 | 1340 |
| LiveBench Data Analysis | 48.3% | 51.5% |
| Epoch Capabilities Index | 123.8 | 130.04 |
| LiveBench | 43.5% | 50% |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 52.5% |
| LMCA | — | 12.3% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Gemma 3 27B: 25.9 (#265)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LiveBench Math | 38% | 55.4% |
| LMArena Math | 1252 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 74% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Gemma 3 27B: 25.5 (#261)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| Confabulations | 30.1% | 40.3% |
| Vectara Hallucination Rate | 5.1% | 7.4% |
| LMArena Expert | 1211 | 1304 |
| GPQA Diamond | — | 47.7% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Gemma 3 27B leads
Amazon Nova Pro: 25.0 (#126), Gemma 3 27B: 32.6 (#100)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LMArena Vision | 980 | 1164 |
| GeoBench | — | 52% |
Multilingual Gemma 3 27B leads
Amazon Nova Pro: 39.7 (#223), Gemma 3 27B: 46.9 (#155)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1234 | 1334 |
| LMArena Chinese | 1244 | 1346 |
| LMArena French | 1271 | 1368 |
| LMArena German | 1243 | 1362 |
| LMArena Japanese | 1200 | 1287 |
| LMArena Korean | 1203 | 1308 |
| LMArena Russian | 1240 | 1349 |
| LMArena Spanish | 1182 | 1349 |
Instruction Following Gemma 3 27B leads
Amazon Nova Pro: 64.9 (#226), Gemma 3 27B: 70.6 (#160)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 74.9% |
| LMArena Instruction Following | 1235 | 1321 |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Gemma 3 27B: 27.6 (#293)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1255 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
Amazon Nova Pro: 43.9 (#226), Gemma 3 27B: 52.5 (#168)
| Benchmark | Amazon Nova Pro | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1259 | 1358 |
| LMArena Creative Writing | 1212 | 1346 |
| Short-Story Creative Writing | 60.5% | 79.9% |
| LMArena Multi-Turn | 1246 | 1345 |
| LiveBench Language | 37% | 34.6% |
| EQ-Bench Creative Writing | — | 1266 |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than Gemma 3 27B?
Amazon Nova Pro and Gemma 3 27B score almost the same on the Noometry Index (31.0 vs 30.8), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Pro or Gemma 3 27B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Gemma 3 27B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 131K.
How many benchmarks do Amazon Nova Pro and Gemma 3 27B share?
30 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemma 3 27B has 43.