# Amazon Nova Micro vs Gemma 4 31B IT

> Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 2.5× less per token, which makes it the better buy when Gemma 4 31B IT's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-micro-vs-gemma-4-31b-it
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 39.5.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.09 / $0.34 for Gemma 4 31B IT.
- Gemma 4 31B IT accepts more context: 262K tokens versus 128K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| Provider | Amazon | Google |
| Noometry Index | 30.4 | 43.5 |
| Rank | 294 | 90 |
| Context | 128K | 262K |
| Input $/M | $0.035 | $0.09 |
| Output $/M | $0.14 | $0.34 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Micro: 30.5 (#295)
- Gemma 4 31B IT: 42.3 (#108)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1218 | 1459 |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 925.5 |

## Agentic & Tool Use

- Amazon Nova Micro: 22.1 (#132)
- Gemma 4 31B IT: —

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |

## Reasoning

- Amazon Nova Micro: 17.4 (#294)
- Gemma 4 31B IT: 27.2 (#122)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1448 |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| LiveBench Reasoning | 25.1% | — |
| DTBench | — | 82.7% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| Epoch Capabilities Index | — | 142.74 |
| LiveBench | 29.6% | — |

## Math

- Amazon Nova Micro: 26.9 (#254)
- Gemma 4 31B IT: 43.2 (#81)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Math | 1206 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |

## Knowledge

- Amazon Nova Micro: 29.6 (#237)
- Gemma 4 31B IT: 37.9 (#151)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 7.4% |
| LMArena Expert | 1184 | 1465 |
| GPQA Diamond | — | 75.8% |
| SimpleQA Verified | — | 10.4% |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |

## Multimodal

- Amazon Nova Micro: —
- Gemma 4 31B IT: 41.6 (#34)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1277 |
| LMArena Document | — | 1425 |

## Multilingual

- Amazon Nova Micro: 36.5 (#239)
- Gemma 4 31B IT: 53.8 (#57)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1186 | 1431 |
| LMArena Chinese | 1209 | 1476 |
| LMArena French | 1238 | 1435 |
| LMArena Russian | 1185 | 1460 |
| LMArena Spanish | 1225 | 1444 |
| LMArena German | 1192 | — |
| LMArena Japanese | 1154 | — |
| LMArena Korean | 1150 | — |

## Instruction Following

- Amazon Nova Micro: 56.3 (#272)
- Gemma 4 31B IT: 75.5 (#61)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1174 | 1433 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |

## Long Context

- Amazon Nova Micro: 36.5 (#229)
- Gemma 4 31B IT: 44.2 (#71)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1205 | 1446 |

## Writing & Preference

- Amazon Nova Micro: 39.5 (#247)
- Gemma 4 31B IT: 60.5 (#96)

| Benchmark | Amazon Nova Micro | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1208 | 1443 |
| LMArena Creative Writing | 1172 | 1415 |
| LMArena Multi-Turn | 1178 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| WildBench | 74.3% | — |
| EQ-Bench 4 | — | 1120 |
| LiveBench Language | 15.8% | — |

## FAQ

### Is Amazon Nova Micro better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 2.5× less per token, which makes it the better buy when Gemma 4 31B IT's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Micro or Gemma 4 31B IT?

Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Gemma 4 31B IT lists at $0.09 and $0.34.

### Is Amazon Nova Micro or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 30.5 in the Noometry coding category.

### Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 128K.

### How many benchmarks do Amazon Nova Micro and Gemma 4 31B IT share?

15 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Gemma 4 31B IT has 35.