# Amazon Nova Pro vs GPT-4.5

> GPT-4.5 is the stronger model overall, scoring 36.9 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and GPT-4.5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 44.1.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 71.1% for GPT-4.5.

## Snapshot

| | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.5 | 36.9 |
| Rank | 278 | 200 |
| Context | 300K | — |
| Input $/M | $0.80 | — |
| Output $/M | $3.20 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- GPT-4.5: 41.8 (#102)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LiveBench Coding | 38.1% | 75.2% |
| LMArena Coding | 1270 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- GPT-4.5: 27.6 (#92)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| Cybench | — | 17.5% |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- GPT-4.5: 14.1 (#320)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LiveBench Reasoning | 32.6% | 71.1% |
| LMArena Hard Prompts | 1246 | 1404 |
| LiveBench Data Analysis | 48.3% | 64.3% |
| Epoch Capabilities Index | 123.75 | 136.74 |
| LiveBench | 43.5% | 69% |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| ForecastBench | — | 61.7 |

## Math

- Amazon Nova Pro: 26.4 (#240)
- GPT-4.5: 31.0 (#200)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LiveBench Math | 38% | 69.3% |
| LMArena Math | 1252 | 1412 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 78.6% |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- GPT-4.5: 32.4 (#205)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| Humanity's Last Exam | 4.4% | 5.4% |
| Confabulations | 30.1% | 13.6% |
| LMArena Expert | 1211 | 1394 |
| GPQA Diamond | — | 68.7% |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 24.5 (#121)
- GPT-4.5: 37.0 (#68)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LMArena Vision | 980 | 1195 |
| VPCT | — | 45% |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- GPT-4.5: 52.7 (#78)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1413 |
| LMArena Chinese | 1244 | 1421 |
| LMArena French | 1270 | 1417 |
| LMArena German | 1243 | 1457 |
| LMArena Japanese | 1200 | 1416 |
| LMArena Korean | 1203 | 1392 |
| LMArena Russian | 1240 | 1419 |
| LMArena Spanish | 1182 | — |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- GPT-4.5: 72.8 (#129)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 72.3% |
| LMArena Instruction Following | 1235 | 1404 |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- GPT-4.5: 40.4 (#150)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- GPT-4.5: 57.1 (#129)

| Benchmark | Amazon Nova Pro | GPT-4.5 |
|---|---|---|
| LMArena Text | 1259 | 1417 |
| LMArena Creative Writing | 1212 | 1394 |
| Short-Story Creative Writing | 60.5% | 75.6% |
| LMArena Multi-Turn | 1245 | 1444 |
| LiveBench Language | 37% | 61.5% |
| EQ-Bench Creative Writing | — | 1258 |
| WildBench | 77.7% | — |

## FAQ

### Is Amazon Nova Pro better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 36.9 to 30.5 on the Noometry Index.

### Is Amazon Nova Pro or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 34.6 in the Noometry coding category.

### How many benchmarks do Amazon Nova Pro and GPT-4.5 share?

28 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-4.5 has 42.