# Amazon Nova Pro vs GPT-5.2

> GPT-5.2 is the stronger model overall, scoring 54.1 to 30.5 on the Noometry Index. Amazon Nova Pro costs 3.4× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-gpt-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 leads 59.8 to 26.4.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 55.9% for GPT-5.2.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-5.2 accepts more context: 400K tokens versus 300K.

## Snapshot

| | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.5 | 54.1 |
| Rank | 278 | 31 |
| Context | 300K | 400K |
| Input $/M | $0.80 | $1.75 |
| Output $/M | $3.20 | $14 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- GPT-5.2: 52.2 (#32)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Coding | 1270 | 1447 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1415 |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
| WeirdML | — | 72.2% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- GPT-5.2: 40.0 (#24)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 55.9% |
| Terminal-Bench | — | 64.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| TheAgentCompany | 1.7% | — |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- GPT-5.2: 50.1 (#33)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1445 |
| Epoch Capabilities Index | 123.75 | 153.45 |
| ARC-AGI-2 | — | 52.9% |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| Chess Puzzles | — | 49% |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 23% |
| DTBench | — | 90.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 43.9% |
| ForecastBench | — | 60.1 |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 26.4 (#240)
- GPT-5.2: 59.8 (#32)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Math | 1252 | 1439 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 15% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- GPT-5.2: 59.2 (#29)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| Humanity's Last Exam | 4.4% | 27.8% |
| Vectara Hallucination Rate | 5.1% | 8.4% |
| LMArena Expert | 1211 | 1445 |
| GPQA Diamond | — | 91.4% |
| SimpleQA Verified | — | 37.1% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 24.5 (#121)
- GPT-5.2: 50.9 (#7)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Vision | 980 | 1268 |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- GPT-5.2: 53.6 (#63)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1234 | 1425 |
| LMArena Chinese | 1244 | 1460 |
| LMArena French | 1270 | 1456 |
| LMArena German | 1243 | 1448 |
| LMArena Japanese | 1200 | 1421 |
| LMArena Korean | 1203 | 1390 |
| LMArena Russian | 1240 | 1440 |
| LMArena Spanish | 1182 | 1433 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- GPT-5.2: 74.9 (#83)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1417 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- GPT-5.2: 44.0 (#74)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1255 | 1428 |
| CL-bench | — | 18.2% |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- GPT-5.2: 67.0 (#30)

| Benchmark | Amazon Nova Pro | GPT-5.2 |
|---|---|---|
| LMArena Text | 1259 | 1439 |
| LMArena Creative Writing | 1212 | 1402 |
| LMArena Multi-Turn | 1245 | 1458 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1703 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than GPT-5.2?

GPT-5.2 is the stronger model overall, scoring 54.1 to 30.5 on the Noometry Index. Amazon Nova Pro costs 3.4× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Pro or GPT-5.2?

Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GPT-5.2 lists at $1.75 and $14.

### Is Amazon Nova Pro or GPT-5.2 better for coding?

GPT-5.2 scores higher on coding benchmarks: 52.2 versus 34.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.2 does, with 400K tokens against 300K.

### How many benchmarks do Amazon Nova Pro and GPT-5.2 share?

22 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5.2 has 67.