# Amazon Nova Pro vs Claude Sonnet 5

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 30.5 on the Noometry Index. Amazon Nova Pro costs 2.9× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-claude-sonnet-5
- 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 Claude Sonnet 5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 26.4.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 300K.

## Snapshot

| | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 30.5 | 54.5 |
| Rank | 278 | 26 |
| Context | 300K | 1M |
| Input $/M | $0.80 | $2 |
| Output $/M | $3.20 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- Claude Sonnet 5: 55.5 (#20)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Coding | 1270 | 1483 |
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.7% |
| CursorBench | — | 34.1% |
| LMArena WebDev | — | 1540 |
| SciCode | — | 53.6% |
| GSO | — | 37.3% |
| WeirdML | — | 68.8% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,463 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- Claude Sonnet 5: 42.7 (#16)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| APEX-Agents | — | 54.5% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| GBAEval | — | 65.3% |
| LMArena Search | — | 1194 |
| Vending-Bench 2 | — | 6,378 |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- Claude Sonnet 5: 48.2 (#37)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1461 |
| Epoch Capabilities Index | 123.75 | 156.34 |
| SimpleBench | — | 60.6% |
| NYT Connections (extended) | — | 75.1% |
| CritPt | — | 16.9% |
| Chess Puzzles | — | 35% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 35% |
| DTBench | — | 92.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 50% |
| Surface Evolver Bench | — | 60% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | — | 61.1 |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 26.4 (#240)
- Claude Sonnet 5: 66.1 (#21)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Math | 1252 | 1467 |
| FrontierMath (Tiers 1-3) | — | 65.6% |
| FrontierMath Tier 4 | — | 29.3% |
| OTIS Mock AIME 2024-2025 | — | 94.7% |
| ProofBench | — | 77% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- Claude Sonnet 5: 55.7 (#42)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Expert | 1211 | 1491 |
| GPQA Diamond | — | 90.5% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 33.7% |
| 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)
- Claude Sonnet 5: 42.4 (#26)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Vision | 980 | 1275 |
| Blueprint-Bench 2 | — | 24.9% |
| LMArena Document | — | 1466 |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- Claude Sonnet 5: 54.0 (#55)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | 1234 | 1431 |
| LMArena Chinese | 1244 | 1475 |
| LMArena French | 1270 | 1457 |
| LMArena German | 1243 | 1448 |
| LMArena Japanese | 1200 | 1422 |
| LMArena Korean | 1203 | 1411 |
| LMArena Russian | 1240 | 1452 |
| LMArena Spanish | 1182 | 1436 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- Claude Sonnet 5: 76.6 (#39)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1453 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- Claude Sonnet 5: 44.8 (#53)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1464 |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- Claude Sonnet 5: 69.4 (#24)

| Benchmark | Amazon Nova Pro | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | 1259 | 1443 |
| LMArena Creative Writing | 1212 | 1416 |
| LMArena Multi-Turn | 1245 | 1454 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1794 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1236 |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Claude Sonnet 5?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 30.5 on the Noometry Index. Amazon Nova Pro costs 2.9× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Pro or Claude Sonnet 5?

Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Amazon Nova Pro or Claude Sonnet 5 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 34.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 300K.

### How many benchmarks do Amazon Nova Pro and Claude Sonnet 5 share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude Sonnet 5 has 51.