Model comparison
Amazon Nova Micro vs Gemma 3 27B
Amazon Nova Micro and Gemma 3 27B score almost the same on the Noometry Index (30.4 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Amazon Nova Micro scores higher in 5 categories and Gemma 3 27B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 27B leads 70.6 to 56.3.
- The biggest single-benchmark swing is LiveBench Instruction Following: 48% for Amazon Nova Micro and 74.9% for Gemma 3 27B.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.08 / $0.16 for Gemma 3 27B.
- Gemma 3 27B accepts more context: 131K tokens versus 128K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Gemma 3 27B | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 30.4 | 30.8 |
| Released | 2024-12-03 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 10K | 8K |
| Input $ / M tokens | $0.035 | $0.08 |
| Output $ / M tokens | $0.14 | $0.16 |
| Results tracked | 32 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Micro leads
Amazon Nova Micro: 30.5 (#295), Gemma 3 27B: 22.5 (#334)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LiveBench Coding | 20.2% | 39.9% |
| LMArena Coding | 1218 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
Agentic & Tool Use Gemma 3 27B leads
Amazon Nova Micro: 22.1 (#132), Gemma 3 27B: 25.1 (#110)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 29.5% |
Reasoning Too close to call
Amazon Nova Micro: 17.4 (#294), Gemma 3 27B: 16.7 (#301)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LiveBench Reasoning | 25.1% | 43.8% |
| LMArena Hard Prompts | 1191 | 1340 |
| LiveBench Data Analysis | 34% | 51.5% |
| LiveBench | 29.6% | 50% |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 52.5% |
| LMCA | — | 12.3% |
| Epoch Capabilities Index | — | 130.04 |
Math Amazon Nova Micro leads
Amazon Nova Micro: 26.9 (#254), Gemma 3 27B: 25.9 (#265)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LiveBench Math | 34.5% | 55.4% |
| LMArena Math | 1206 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| Omni-MATH | 21.4% | — |
| MATH Level 5 | — | 74% |
Knowledge Amazon Nova Micro leads
Amazon Nova Micro: 29.6 (#237), Gemma 3 27B: 25.5 (#261)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 7.4% |
| LMArena Expert | 1184 | 1304 |
| GPQA Diamond | — | 47.7% |
| MMLU-Pro | 51.1% | — |
| Confabulations | — | 40.3% |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
Multilingual Gemma 3 27B leads
Amazon Nova Micro: 36.5 (#239), Gemma 3 27B: 46.9 (#155)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1186 | 1334 |
| LMArena Chinese | 1209 | 1346 |
| LMArena French | 1238 | 1368 |
| LMArena German | 1192 | 1362 |
| LMArena Japanese | 1154 | 1287 |
| LMArena Korean | 1150 | 1308 |
| LMArena Russian | 1185 | 1349 |
| LMArena Spanish | 1225 | 1349 |
Instruction Following Gemma 3 27B leads
Amazon Nova Micro: 56.3 (#272), Gemma 3 27B: 70.6 (#160)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LiveBench Instruction Following | 48% | 74.9% |
| LMArena Instruction Following | 1174 | 1321 |
| IFEval | 76% | — |
Long Context Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#229), Gemma 3 27B: 27.6 (#293)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1205 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
Amazon Nova Micro: 39.5 (#247), Gemma 3 27B: 52.5 (#168)
| Benchmark | Amazon Nova Micro | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1208 | 1358 |
| LMArena Creative Writing | 1172 | 1346 |
| LMArena Multi-Turn | 1178 | 1345 |
| LiveBench Language | 15.8% | 34.6% |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| WildBench | 74.3% | — |
Frequently asked questions
Is Amazon Nova Micro better than Gemma 3 27B?
Amazon Nova Micro and Gemma 3 27B score almost the same on the Noometry Index (30.4 vs 30.8), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Micro or Gemma 3 27B?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Gemma 3 27B lists at $0.08 and $0.16.
Is Amazon Nova Micro or Gemma 3 27B better for coding?
Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Gemma 3 27B does, with 131K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Gemma 3 27B share?
26 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Gemma 3 27B has 43.