# Amazon Nova Micro vs Phi 3 Mini 4k Instruct

> Amazon Nova Micro is the stronger model overall, scoring 30.4 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-micro-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Amazon Nova Micro scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Micro leads 39.5 to 27.6.
- The biggest single-benchmark swing is LiveBench Math: 34.5% for Amazon Nova Micro and 15.7% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 30.4 | 27.9 |
| Rank | 294 | 328 |
| Context | 128K | — |
| Input $/M | $0.035 | — |
| Output $/M | $0.14 | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Micro: 30.5 (#295)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 20.2% | 15.5% |
| LMArena Coding | 1218 | 1093 |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

- Amazon Nova Micro: 22.1 (#132)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |

## Reasoning

- Amazon Nova Micro: 17.4 (#294)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 25.1% | 26.8% |
| LMArena Hard Prompts | 1191 | 1072 |
| LiveBench Data Analysis | 34% | 34.7% |
| LiveBench | 29.6% | 22.4% |
| Chess Puzzles | — | 0% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |

## Math

- Amazon Nova Micro: 26.9 (#254)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 34.5% | 15.7% |
| LMArena Math | 1206 | 1111 |
| Omni-MATH | 21.4% | — |

## Knowledge

- Amazon Nova Micro: 29.6 (#237)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1184 | 1045 |
| MMLU | 70.8% | 68.8% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- Amazon Nova Micro: 36.5 (#239)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1186 | 1021 |
| LMArena Chinese | 1209 | 1021 |
| LMArena French | 1238 | 1076 |
| LMArena German | 1192 | 1044 |
| LMArena Japanese | 1154 | 935 |
| LMArena Korean | 1150 | 905 |
| LMArena Russian | 1185 | 1022 |
| LMArena Spanish | 1225 | 1085 |

## Instruction Following

- Amazon Nova Micro: 56.3 (#272)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 48% | 39.1% |
| LMArena Instruction Following | 1174 | 1053 |
| IFEval | 76% | — |

## Long Context

- Amazon Nova Micro: 36.5 (#229)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1205 | 1044 |

## Writing & Preference

- Amazon Nova Micro: 39.5 (#247)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1208 | 1073 |
| LMArena Creative Writing | 1172 | 1037 |
| LMArena Multi-Turn | 1178 | 1018 |
| LiveBench Language | 15.8% | 9.2% |
| WildBench | 74.3% | — |

## FAQ

### Is Amazon Nova Micro better than Phi 3 Mini 4k Instruct?

Amazon Nova Micro is the stronger model overall, scoring 30.4 to 27.9 on the Noometry Index.

### Is Amazon Nova Micro or Phi 3 Mini 4k Instruct better for coding?

Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 26.6 in the Noometry coding category.

### How many benchmarks do Amazon Nova Micro and Phi 3 Mini 4k Instruct share?

25 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.