# Amazon Nova Pro vs Claude 3.5 Sonnet

> Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-claude-3-5-sonnet
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Claude 3.5 Sonnet in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude 3.5 Sonnet leads 32.3 to 16.7.
- The biggest single-benchmark swing is LiveBench Coding: 38.1% for Amazon Nova Pro and 67.1% for Claude 3.5 Sonnet.

## Snapshot

| | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.0 | 34.6 |
| Rank | 281 | 231 |
| Context | 300K | — |
| Input $/M | $0.80 | — |
| Output $/M | $3.20 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Claude 3.5 Sonnet: 39.0 (#165)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LiveBench Coding | 38.1% | 67.1% |
| LMArena Coding | 1270 | 1342 |
| Aider Polyglot | — | 51.6% |
| GSO | — | 4.6% |
| WeirdML | — | 40% |
| BigCodeBench Instruct | — | 46.8% |
| BigCodeBench Complete | — | 58.6% |
| CadEval | — | 48% |
| HumanEval+ | — | 81.7% |
| MBPP+ | — | 74.3% |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Claude 3.5 Sonnet: 32.3 (#67)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| TheAgentCompany | 1.7% | 24% |
| Berkeley Function Calling Leaderboard | 25% | — |
| Cybench | — | 17.5% |
| BALROG | — | 32.6% |
| METR Time Horizons | — | 45.2% |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Claude 3.5 Sonnet: 23.1 (#183)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LiveBench Reasoning | 32.6% | 56.7% |
| LMArena Hard Prompts | 1246 | 1305 |
| LiveBench Data Analysis | 48.3% | 55% |
| Epoch Capabilities Index | 123.8 | 133.55 |
| LiveBench | 43.5% | 59% |
| SimpleBench | — | 41.4% |
| EnigmaEval | — | 0.9% |
| DTBench | — | 67.8% |
| ForecastBench | — | 60.7 |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Claude 3.5 Sonnet: 19.2 (#288)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| Omni-MATH | 24.2% | 27.6% |
| LiveBench Math | 38% | 52.3% |
| LMArena Math | 1252 | 1307 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| MATH Level 5 | — | 56.9% |
| FrontierMath (Feb 2025 set) | — | 2.1% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Claude 3.5 Sonnet: 28.6 (#245)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| Humanity's Last Exam | 4.4% | 4.1% |
| MMLU-Pro | 67.3% | 77.7% |
| Confabulations | 30.1% | 19.9% |
| GPQA (HELM) | 44.6% | 56.5% |
| LMArena Expert | 1211 | 1265 |
| MMLU | 82% | 87.3% |
| GPQA Diamond | — | 55.3% |
| Vectara Hallucination Rate | 5.1% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Claude 3.5 Sonnet: 26.5 (#120)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Vision | 980 | 1125 |
| Video-MME | — | 60% |
| GeoBench | — | 62% |
| VPCT | — | 33% |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Claude 3.5 Sonnet: 43.2 (#185)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Non-English | 1234 | 1283 |
| LMArena Chinese | 1244 | 1272 |
| LMArena French | 1271 | 1305 |
| LMArena German | 1243 | 1297 |
| LMArena Japanese | 1200 | 1234 |
| LMArena Korean | 1203 | 1200 |
| LMArena Russian | 1240 | 1306 |
| LMArena Spanish | 1182 | 1290 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Claude 3.5 Sonnet: 68.8 (#182)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 69.3% |
| IFEval | 81.5% | 85.5% |
| LMArena Instruction Following | 1235 | 1297 |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Claude 3.5 Sonnet: 39.9 (#167)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Longer Query | 1255 | 1311 |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Claude 3.5 Sonnet: 52.9 (#164)

| Benchmark | Amazon Nova Pro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Text | 1259 | 1298 |
| LMArena Creative Writing | 1212 | 1292 |
| Short-Story Creative Writing | 60.5% | 80.3% |
| WildBench | 77.7% | 79.2% |
| LMArena Multi-Turn | 1246 | 1326 |
| LiveBench Language | 37% | 53.8% |
| EQ-Bench Creative Writing | — | 1451 |

## FAQ

### Is Amazon Nova Pro better than Claude 3.5 Sonnet?

Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 31.0 on the Noometry Index.

### Is Amazon Nova Pro or Claude 3.5 Sonnet better for coding?

Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 35.1 in the Noometry coding category.

### How many benchmarks do Amazon Nova Pro and Claude 3.5 Sonnet share?

36 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude 3.5 Sonnet has 60.