Model comparison
Amazon Nova Micro vs Gemma 2 27B
Amazon Nova Micro and Gemma 2 27B score almost the same on the Noometry Index (30.4 vs 29.4), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Amazon Nova Micro scores higher in 3 categories and Gemma 2 27B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Micro leads 26.9 to 10.7.
- The biggest single-benchmark swing is LiveBench Language: 15.8% for Amazon Nova Micro and 32.6% for Gemma 2 27B.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Amazon Nova Micro accepts more context: 128K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Gemma 2 27B | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 30.4 | 29.4 |
| Released | 2024-12-03 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | 128K | 8K |
| Max output | 10K | 2K |
| Input $ / M tokens | $0.035 | $0.65 |
| Output $ / M tokens | $0.14 | $0.65 |
| Results tracked | 32 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Amazon Nova Micro: 30.5 (#295), Gemma 2 27B: 34.1 (#246)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LiveBench Coding | 20.2% | 36% |
| LMArena Coding | 1218 | 1211 |
| BigCodeBench Instruct | — | 42.8% |
| BigCodeBench Complete | — | 52.5% |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 22.1 (#132), Gemma 2 27B: —
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), Gemma 2 27B: 15.3 (#315)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LiveBench Reasoning | 25.1% | 28.1% |
| LMArena Hard Prompts | 1191 | 1198 |
| LiveBench Data Analysis | 34% | 47.9% |
| LiveBench | 29.6% | 38.2% |
| DTBench | — | 48% |
| LMCA | — | 7.1% |
| Epoch Capabilities Index | — | 122.08 |
Math Amazon Nova Micro leads
Amazon Nova Micro: 26.9 (#254), Gemma 2 27B: 10.7 (#311)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LiveBench Math | 34.5% | 26.5% |
| LMArena Math | 1206 | 1212 |
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| Omni-MATH | 21.4% | — |
| MATH Level 5 | — | 27.9% |
Knowledge Amazon Nova Micro leads
Amazon Nova Micro: 29.6 (#237), Gemma 2 27B: 19.0 (#280)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LMArena Expert | 1184 | 1172 |
| MMLU | 70.8% | 75.7% |
| GPQA Diamond | — | 36.5% |
| MMLU-Pro | 51.1% | — |
| Confabulations | — | 27.1% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual Gemma 2 27B leads
Amazon Nova Micro: 36.5 (#239), Gemma 2 27B: 38.6 (#226)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1186 | 1217 |
| LMArena Chinese | 1209 | 1221 |
| LMArena French | 1238 | 1247 |
| LMArena German | 1192 | 1209 |
| LMArena Japanese | 1154 | 1175 |
| LMArena Korean | 1150 | 1174 |
| LMArena Russian | 1185 | 1234 |
| LMArena Spanish | 1225 | 1228 |
Instruction Following Gemma 2 27B leads
Amazon Nova Micro: 56.3 (#272), Gemma 2 27B: 60.5 (#249)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LiveBench Instruction Following | 48% | 58.1% |
| LMArena Instruction Following | 1174 | 1206 |
| IFEval | 76% | — |
Long Context Too close to call
Amazon Nova Micro: 36.5 (#229), Gemma 2 27B: 37.3 (#218)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1205 | 1231 |
Writing & Preference Gemma 2 27B leads
Amazon Nova Micro: 39.5 (#247), Gemma 2 27B: 44.2 (#225)
| Benchmark | Amazon Nova Micro | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1208 | 1231 |
| LMArena Creative Writing | 1172 | 1241 |
| LMArena Multi-Turn | 1178 | 1224 |
| LiveBench Language | 15.8% | 32.6% |
| WildBench | 74.3% | — |
Frequently asked questions
Is Amazon Nova Micro better than Gemma 2 27B?
Amazon Nova Micro and Gemma 2 27B score almost the same on the Noometry Index (30.4 vs 29.4), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Micro or Gemma 2 27B?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Amazon Nova Micro or Gemma 2 27B better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Micro does, with 128K tokens against 8K.
How many benchmarks do Amazon Nova Micro and Gemma 2 27B share?
25 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Gemma 2 27B has 34.