# Amazon Nova Micro vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 30.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-micro-vs-step-3
- 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 Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 39.5.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Micro | Step 3 |
|---|---|---|
| Provider | Amazon | StepFun |
| Noometry Index | 30.4 | 40.5 |
| Rank | 294 | 149 |
| Context | 128K | — |
| Input $/M | $0.035 | — |
| Output $/M | $0.14 | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Micro: 30.5 (#295)
- Step 3: 40.1 (#147)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Coding | 1218 | 1367 |
| LiveBench Coding | 20.2% | — |

## Agentic & Tool Use

- Amazon Nova Micro: 22.1 (#132)
- Step 3: —

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |

## Reasoning

- Amazon Nova Micro: 17.4 (#294)
- Step 3: 28.4 (#105)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| LiveBench | 29.6% | — |

## Math

- Amazon Nova Micro: 26.9 (#254)
- Step 3: 37.6 (#148)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Math | 1206 | 1366 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |

## Knowledge

- Amazon Nova Micro: 29.6 (#237)
- Step 3: 36.8 (#164)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Expert | 1184 | 1333 |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |

## Multimodal

- Amazon Nova Micro: —
- Step 3: 35.5 (#86)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Amazon Nova Micro: 36.5 (#239)
- Step 3: 46.3 (#159)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Non-English | 1186 | 1327 |
| LMArena Chinese | 1209 | 1397 |
| LMArena German | 1192 | 1371 |
| LMArena Korean | 1150 | 1269 |
| LMArena Russian | 1185 | 1331 |
| LMArena Spanish | 1225 | 1371 |
| LMArena French | 1238 | — |
| LMArena Japanese | 1154 | — |

## Instruction Following

- Amazon Nova Micro: 56.3 (#272)
- Step 3: 70.4 (#164)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1332 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |

## Long Context

- Amazon Nova Micro: 36.5 (#229)
- Step 3: 40.3 (#157)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Longer Query | 1205 | 1326 |

## Writing & Preference

- Amazon Nova Micro: 39.5 (#247)
- Step 3: 54.3 (#151)

| Benchmark | Amazon Nova Micro | Step 3 |
|---|---|---|
| LMArena Text | 1208 | 1350 |
| LMArena Creative Writing | 1172 | 1321 |
| LMArena Multi-Turn | 1178 | 1341 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |

## FAQ

### Is Amazon Nova Micro better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 30.4 on the Noometry Index.

### Is Amazon Nova Micro or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 30.5 in the Noometry coding category.

### How many benchmarks do Amazon Nova Micro and Step 3 share?

15 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Step 3 has 17.
