# Amazon Nova Pro vs Claude Opus 4.5

> Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 31.0 on the Noometry Index. Amazon Nova Pro costs 7.1× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-claude-opus-4-5
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Claude Opus 4.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Opus 4.5 leads 47.3 to 16.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 77.5% for Claude Opus 4.5.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- Amazon Nova Pro accepts more context: 300K tokens versus 200K.

## Snapshot

| | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.0 | 50.5 |
| Rank | 281 | 47 |
| Context | 300K | 200K |
| Input $/M | $0.80 | $5 |
| Output $/M | $3.20 | $25 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Claude Opus 4.5: 54.8 (#27)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Coding | 1270 | 1504 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | — | 76.8% |
| LMArena WebDev | — | 1494 |
| SWE-bench Multilingual | — | 70.7% |
| GSO | — | 26.5% |
| WeirdML | — | 63.7% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,025 |
| AlgoTune | — | 1.77 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Claude Opus 4.5: 47.3 (#12)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 77.5% |
| Terminal-Bench | — | 63.1% |
| GDPval | — | 45.5% |
| Remote Labor Index | — | 3.8% |
| TheAgentCompany | 1.7% | — |
| τ²-bench Airline | — | 84% |
| τ²-bench Banking | — | 24.7% |
| τ²-bench Retail | — | 79.6% |
| τ²-bench Telecom | — | 92.3% |
| Cybench | — | 82% |
| DeepResearch Bench | — | 54.8% |
| OSWorld | — | 66.3% |
| BALROG | — | 43.5% |
| LMArena Search | — | 1180 |
| METR Time Horizons | — | 75% |
| Vending-Bench 2 | — | 4,967 |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Claude Opus 4.5: 42.6 (#51)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1476 |
| Epoch Capabilities Index | 123.8 | 150.09 |
| ARC-AGI-2 | — | 37.6% |
| SimpleBench | — | 62% |
| Kagi LLM Benchmark | — | 80.2% |
| NYT Connections (extended) | — | 52.5% |
| ARC-AGI-1 | — | 80% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 11.9% |
| EBR-Bench | — | 14.3% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 22% |
| DTBench | — | 89.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 44.5% |
| ForecastBench | — | 60.7 |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Claude Opus 4.5: 38.6 (#132)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Math | 1252 | 1463 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 86.1% |
| ProofBench | — | 36% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 20.7% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Claude Opus 4.5: 56.5 (#44)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| Humanity's Last Exam | 4.4% | 25.2% |
| Vectara Hallucination Rate | 5.1% | 10.9% |
| LMArena Expert | 1211 | 1487 |
| GPQA Diamond | — | 86% |
| SimpleQA Verified | — | 45.7% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Claude Opus 4.5: 31.4 (#107)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Vision | 980 | — |
| GeoBench | — | 75% |
| VPCT | — | 40% |
| Furniture Assembly | — | 28.3% |
| LMArena Document | — | 1462 |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Claude Opus 4.5: 54.3 (#47)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1438 |
| LMArena Chinese | 1244 | 1470 |
| LMArena French | 1271 | 1471 |
| LMArena German | 1243 | 1449 |
| LMArena Japanese | 1200 | 1416 |
| LMArena Korean | 1203 | 1424 |
| LMArena Russian | 1240 | 1447 |
| LMArena Spanish | 1182 | 1458 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Claude Opus 4.5: 77.5 (#19)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1478 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Claude Opus 4.5: 46.5 (#22)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1480 |
| CL-bench | — | 21.1% |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Claude Opus 4.5: 68.1 (#28)

| Benchmark | Amazon Nova Pro | Claude Opus 4.5 |
|---|---|---|
| LMArena Text | 1259 | 1451 |
| LMArena Creative Writing | 1212 | 1445 |
| LMArena Multi-Turn | 1246 | 1466 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1687 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Claude Opus 4.5?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 31.0 on the Noometry Index. Amazon Nova Pro costs 7.1× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Pro or Claude Opus 4.5?

Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

### Is Amazon Nova Pro or Claude Opus 4.5 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 200K.

### How many benchmarks do Amazon Nova Pro and Claude Opus 4.5 share?

21 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude Opus 4.5 has 69.