# Amazon Nova Pro vs Phi-4

> Amazon Nova Pro and Phi-4 score almost the same on the Noometry Index (31.0 vs 31.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Amazon Nova Pro scores higher in 7 categories and Phi-4 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 20.8.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 47.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Phi-4 |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 31.0 | 31.2 |
| Rank | 281 | 279 |
| Context | 300K | 128K |
| Input $/M | $0.80 | $0.07 |
| Output $/M | $3.20 | $0.14 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Phi-4: 34.4 (#239)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LiveBench Coding | 38.1% | 30.7% |
| LMArena Coding | 1270 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Phi-4: 22.8 (#128)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 28.8% |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 11.6% |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Phi-4: 17.7 (#291)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LiveBench Reasoning | 32.6% | 47.8% |
| LMArena Hard Prompts | 1246 | 1220 |
| LiveBench Data Analysis | 48.3% | 45.2% |
| Epoch Capabilities Index | 123.8 | 130.42 |
| LiveBench | 43.5% | 41.6% |
| Chess Puzzles | — | 1% |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Phi-4: 20.8 (#285)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LiveBench Math | 38% | 42% |
| LMArena Math | 1252 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Phi-4: 32.6 (#209)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| Confabulations | 30.1% | 29.4% |
| Vectara Hallucination Rate | 5.1% | 3.7% |
| LMArena Expert | 1211 | 1203 |
| MMLU | 82% | 84.8% |
| GPQA Diamond | — | 56.1% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| GPQA (HELM) | 44.6% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Phi-4: —

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Phi-4: 37.2 (#237)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LMArena Non-English | 1234 | 1197 |
| LMArena Chinese | 1244 | 1212 |
| LMArena French | 1271 | 1224 |
| LMArena German | 1243 | 1222 |
| LMArena Japanese | 1200 | 1158 |
| LMArena Korean | 1203 | 1151 |
| LMArena Russian | 1240 | 1209 |
| LMArena Spanish | 1182 | 1234 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Phi-4: 60.4 (#251)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 58.4% |
| LMArena Instruction Following | 1235 | 1201 |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Phi-4: 36.9 (#226)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1255 | 1217 |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Phi-4: 40.5 (#244)

| Benchmark | Amazon Nova Pro | Phi-4 |
|---|---|---|
| LMArena Text | 1259 | 1217 |
| LMArena Creative Writing | 1212 | 1182 |
| Short-Story Creative Writing | 60.5% | 62.6% |
| LMArena Multi-Turn | 1246 | 1206 |
| LiveBench Language | 37% | 25.6% |
| WildBench | 77.7% | — |

## FAQ

### Is Amazon Nova Pro better than Phi-4?

Amazon Nova Pro and Phi-4 score almost the same on the Noometry Index (31.0 vs 31.2), so choose on price, context window or the category you care about most.

### Which is cheaper, Amazon Nova Pro or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or Phi-4 better for coding?

They score almost the same on coding (35.1 vs 34.4); test both on your own repository before choosing.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 128K.

### How many benchmarks do Amazon Nova Pro and Phi-4 share?

30 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Phi-4 has 37.