# Amazon Nova Pro vs Phi 3 Mini 128k Instruct

> Amazon Nova Pro is the stronger model overall, scoring 30.5 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Amazon Nova Pro scores higher in 7 categories and Phi 3 Mini 128k Instruct in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Pro leads 44.1 to 27.3.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 30.5 | 29.1 |
| Rank | 278 | 303 |
| Context | 300K | — |
| Input $/M | $0.80 | — |
| Output $/M | $3.20 | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1270 | 1040 |
| BigCodeBench Instruct | — | 29.6% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 40.6% |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1028 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.75 | — |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 26.4 (#240)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1252 | 1089 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1211 | 984 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 24.5 (#121)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1234 | 1000 |
| LMArena Chinese | 1244 | 1016 |
| LMArena French | 1270 | 1038 |
| LMArena German | 1243 | 1006 |
| LMArena Japanese | 1200 | 899 |
| LMArena Korean | 1203 | 856 |
| LMArena Russian | 1240 | 1004 |
| LMArena Spanish | 1182 | 1058 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1235 | 1023 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1255 | 996 |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | Amazon Nova Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1259 | 1050 |
| LMArena Creative Writing | 1212 | 1024 |
| LMArena Multi-Turn | 1245 | 989 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Phi 3 Mini 128k Instruct?

Amazon Nova Pro is the stronger model overall, scoring 30.5 to 29.1 on the Noometry Index.

### Is Amazon Nova Pro or Phi 3 Mini 128k Instruct better for coding?

Amazon Nova Pro scores higher on coding benchmarks: 34.6 versus 28.3 in the Noometry coding category.

### How many benchmarks do Amazon Nova Pro and Phi 3 Mini 128k Instruct share?

17 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.