# Amazon Nova Lite vs Phi 3 Small 8k Instruct

> Amazon Nova Lite is the stronger model overall, scoring 31.4 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Amazon Nova Lite scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Lite leads 42.3 to 31.3.
- The biggest single-benchmark swing is LiveBench Reasoning: 36.7% for Amazon Nova Lite and 15.9% for Phi 3 Small 8k Instruct.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 31.4 | 28.8 |
| Rank | 262 | 310 |
| Context | 300K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.24 | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Lite: 32.0 (#266)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 27.5% | 20.3% |
| LMArena Coding | 1239 | 1102 |
| ALE-Bench | 236.25 | — |

## Reasoning

- Amazon Nova Lite: 18.5 (#257)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 36.7% | 15.9% |
| LMArena Hard Prompts | 1220 | 1100 |
| LiveBench Data Analysis | 37.2% | 30.3% |
| LiveBench | 36.4% | 24% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |

## Math

- Amazon Nova Lite: 25.8 (#243)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 36.7% | 17.6% |
| LMArena Math | 1227 | 1151 |
| Omni-MATH | 23.3% | — |

## Knowledge

- Amazon Nova Lite: 26.0 (#254)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1201 | 1067 |
| MMLU | 77% | 75.7% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multimodal

- Amazon Nova Lite: 25.0 (#118)
- Phi 3 Small 8k Instruct: —

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 990 | — |

## Multilingual

- Amazon Nova Lite: 38.2 (#227)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1208 | 1058 |
| LMArena Chinese | 1225 | 1061 |
| LMArena French | 1237 | 1134 |
| LMArena German | 1229 | 1080 |
| LMArena Japanese | 1153 | 966 |
| LMArena Korean | 1153 | 894 |
| LMArena Russian | 1216 | 1111 |
| LMArena Spanish | 1225 | 1111 |

## Instruction Following

- Amazon Nova Lite: 59.6 (#250)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 54.1% | 47.2% |
| LMArena Instruction Following | 1205 | 1087 |
| IFEval | 77.6% | — |

## Long Context

- Amazon Nova Lite: 37.4 (#212)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1234 | 1088 |

## Writing & Preference

- Amazon Nova Lite: 42.3 (#232)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | Amazon Nova Lite | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1229 | 1110 |
| LMArena Creative Writing | 1197 | 1083 |
| LMArena Multi-Turn | 1199 | 1068 |
| LiveBench Language | 25.9% | 12.9% |
| WildBench | 75% | — |

## FAQ

### Is Amazon Nova Lite better than Phi 3 Small 8k Instruct?

Amazon Nova Lite is the stronger model overall, scoring 31.4 to 28.8 on the Noometry Index.

### Is Amazon Nova Lite or Phi 3 Small 8k Instruct better for coding?

Amazon Nova Lite scores higher on coding benchmarks: 32.0 versus 27.4 in the Noometry coding category.

### How many benchmarks do Amazon Nova Lite and Phi 3 Small 8k Instruct share?

25 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Phi 3 Small 8k Instruct has 32.