# Amazon Nova Lite vs Claude 3.7 Sonnet

> Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-claude-3-7-sonnet
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Amazon Nova Lite scores higher in 1 category and Claude 3.7 Sonnet in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Claude 3.7 Sonnet leads 72.9 to 59.3.
- The biggest single-benchmark swing is LiveBench Reasoning: 36.7% for Amazon Nova Lite and 87.8% for Claude 3.7 Sonnet.

## Snapshot

| | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.9 | 39.5 |
| Rank | 265 | 164 |
| Context | 300K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.24 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Lite: 32.5 (#270)
- Claude 3.7 Sonnet: 40.6 (#136)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LiveBench Coding | 27.5% | 74.5% |
| LMArena Coding | 1239 | 1361 |
| SWE-bench Verified | — | 61% |
| SWE-bench Verified (bash only) | — | 52.8% |
| Aider Polyglot | — | 64.9% |
| GSO | — | 3.8% |
| CadEval | — | 54% |
| ALE-Bench | 236.25 | — |

## Agentic & Tool Use

- Amazon Nova Lite: —
- Claude 3.7 Sonnet: 34.1 (#50)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| TheAgentCompany | — | 30.9% |
| Cybench | — | 20% |
| DeepResearch Bench | — | 43.6% |
| OSWorld | — | 35.8% |
| METR Time Horizons | — | 60% |

## Reasoning

- Amazon Nova Lite: 19.3 (#260)
- Claude 3.7 Sonnet: 18.6 (#277)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LiveBench Reasoning | 36.7% | 87.8% |
| LMArena Hard Prompts | 1220 | 1333 |
| LiveBench Data Analysis | 37.2% | 74% |
| LiveBench | 36.4% | 76.1% |
| ARC-AGI-2 | — | 0.9% |
| SimpleBench | — | 46.4% |
| ARC-AGI-1 | — | 28.6% |
| EnigmaEval | — | 4.2% |
| Epoch Capabilities Index | — | 141.16 |
| ForecastBench | — | 61.8 |

## Math

- Amazon Nova Lite: 27.8 (#247)
- Claude 3.7 Sonnet: 37.5 (#153)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| Omni-MATH | 23.3% | 33% |
| LiveBench Math | 36.7% | 79% |
| LMArena Math | 1227 | 1337 |
| OTIS Mock AIME 2024-2025 | — | 57.8% |
| MATH Level 5 | — | 91.2% |
| FrontierMath (Feb 2025 set) | — | 4.1% |

## Knowledge

- Amazon Nova Lite: 26.3 (#259)
- Claude 3.7 Sonnet: 39.8 (#130)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| Humanity's Last Exam | 3.6% | 8% |
| MMLU-Pro | 60% | 78.4% |
| GPQA (HELM) | 39.7% | 60.8% |
| LMArena Expert | 1201 | 1321 |
| GPQA Diamond | — | 79.7% |
| Confabulations | — | 14.7% |
| Vectara Hallucination Rate | 6.1% | — |
| MMLU | 77% | — |

## Multimodal

- Amazon Nova Lite: 25.5 (#123)
- Claude 3.7 Sonnet: 33.7 (#95)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Vision | 990 | 1169 |
| GeoBench | — | 68% |
| VPCT | — | 39% |
| SpatialViz-Bench | — | 33.9% |

## Multilingual

- Amazon Nova Lite: 38.0 (#232)
- Claude 3.7 Sonnet: 44.1 (#179)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Non-English | 1208 | 1296 |
| LMArena Chinese | 1225 | 1299 |
| LMArena French | 1237 | 1303 |
| LMArena German | 1229 | 1301 |
| LMArena Japanese | 1153 | 1267 |
| LMArena Korean | 1153 | 1249 |
| LMArena Russian | 1216 | 1311 |
| LMArena Spanish | 1226 | 1298 |

## Instruction Following

- Amazon Nova Lite: 59.3 (#255)
- Claude 3.7 Sonnet: 72.9 (#125)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LiveBench Instruction Following | 54.1% | 81.3% |
| IFEval | 77.6% | 83.4% |
| LMArena Instruction Following | 1205 | 1352 |

## Long Context

- Amazon Nova Lite: 37.4 (#217)
- Claude 3.7 Sonnet: 50.3 (#10)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Longer Query | 1234 | 1373 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Amazon Nova Lite: 42.1 (#237)
- Claude 3.7 Sonnet: 54.4 (#150)

| Benchmark | Amazon Nova Lite | Claude 3.7 Sonnet |
|---|---|---|
| LMArena Text | 1229 | 1314 |
| LMArena Creative Writing | 1197 | 1332 |
| WildBench | 75% | 81.4% |
| LMArena Multi-Turn | 1199 | 1339 |
| LiveBench Language | 25.9% | 59.9% |
| Short-Story Creative Writing | — | 81.1% |
| EQ-Bench Creative Writing | — | 1412 |

## FAQ

### Is Amazon Nova Lite better than Claude 3.7 Sonnet?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 31.9 on the Noometry Index.

### Is Amazon Nova Lite or Claude 3.7 Sonnet better for coding?

Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 32.5 in the Noometry coding category.

### How many benchmarks do Amazon Nova Lite and Claude 3.7 Sonnet share?

31 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Claude 3.7 Sonnet has 58.