# Amazon Nova Pro vs GPT-5.6 Luna

> GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-gpt-5-6-luna
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5.6 Luna in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 26.4.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 300K.

## Snapshot

| | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.5 | 54.7 |
| Rank | 278 | 24 |
| Context | 300K | 1.05M |
| Input $/M | $0.80 | $0.20 |
| Output $/M | $3.20 | $1.20 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- GPT-5.6 Luna: 53.9 (#25)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Coding | 1270 | 1466 |
| DeepSWE | — | 67.2% |
| FrontierCode | — | 39.8% |
| CursorBench | — | 35.9% |
| LMArena WebDev | — | 1517 |
| SciCode | — | 53.6% |
| WeirdML | — | 60.9% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,667 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- GPT-5.6 Luna: 35.3 (#37)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 45.6% |
| GDP.pdf | — | 22.7% |
| Vending-Bench 2 | — | 4,095 |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- GPT-5.6 Luna: 47.5 (#38)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1452 |
| Epoch Capabilities Index | 123.75 | 156.32 |
| ARC-AGI-2 | — | 59.5% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 49.1% |
| NYT Connections (extended) | — | 69.4% |
| ARC-AGI-1 | — | 88% |
| CritPt | — | 20.6% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 21% |
| DTBench | — | 89.1% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 48.5% |
| Surface Evolver Bench | — | 61.9% |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 26.4 (#240)
- GPT-5.6 Luna: 77.5 (#12)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Math | 1252 | 1455 |
| FrontierMath (Tiers 1-3) | — | 82.1% |
| FrontierMath Tier 4 | — | 61% |
| OTIS Mock AIME 2024-2025 | — | 98.3% |
| ProofBench | — | 60% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- GPT-5.6 Luna: 58.6 (#31)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Expert | 1211 | 1479 |
| GPQA Diamond | — | 91.6% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 41% |
| 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)
- GPT-5.6 Luna: 43.0 (#22)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | 980 | 1259 |
| Blueprint-Bench 2 | — | 22.6% |
| Furniture Assembly | — | 42.5% |
| LMArena Document | — | 1457 |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- GPT-5.6 Luna: 53.0 (#73)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1234 | 1418 |
| LMArena Chinese | 1244 | 1469 |
| LMArena French | 1270 | 1457 |
| LMArena German | 1243 | 1459 |
| LMArena Japanese | 1200 | 1416 |
| LMArena Korean | 1203 | 1414 |
| LMArena Russian | 1240 | 1428 |
| LMArena Spanish | 1182 | 1445 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- GPT-5.6 Luna: 76.0 (#48)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1235 | 1440 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- GPT-5.6 Luna: 43.9 (#78)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1255 | 1437 |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- GPT-5.6 Luna: 68.3 (#27)

| Benchmark | Amazon Nova Pro | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1259 | 1432 |
| LMArena Creative Writing | 1212 | 1397 |
| LMArena Multi-Turn | 1245 | 1433 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1829 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1156 |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than GPT-5.6 Luna?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 30.5 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro or GPT-5.6 Luna?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or GPT-5.6 Luna better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 34.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 300K.

### How many benchmarks do Amazon Nova Pro and GPT-5.6 Luna share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5.6 Luna has 51.