# Amazon Nova Lite vs Claude Sonnet 4.5

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index. Amazon Nova Lite costs 57× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-claude-sonnet-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and Claude Sonnet 4.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.5 to 42.1.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 55.3% for Claude Sonnet 4.5.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Amazon Nova Lite accepts more context: 300K tokens versus 200K.

## Snapshot

| | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.9 | 44.1 |
| Rank | 265 | 81 |
| Context | 300K | 200K |
| Input $/M | $0.06 | $3 |
| Output $/M | $0.24 | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Lite: 32.5 (#270)
- Claude Sonnet 4.5: 47.3 (#61)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Coding | 1239 | 1489 |
| ALE-Bench | 236.25 | 796.15 |
| SWE-bench Verified | — | 71.3% |
| SWE-bench Verified (bash only) | — | 71.4% |
| LMArena WebDev | — | 1393 |
| SWE-bench Multilingual | — | 67% |
| SciCode | — | 44.7% |
| GSO | — | 14.7% |
| WeirdML | — | 47.7% |
| LiveBench Coding | 27.5% | — |
| AlgoTune | — | 1.52 |

## Agentic & Tool Use

- Amazon Nova Lite: —
- Claude Sonnet 4.5: 38.3 (#32)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| Terminal-Bench | — | 46.5% |
| Berkeley Function Calling Leaderboard | — | 73.2% |
| GDPval | — | 42.5% |
| Remote Labor Index | — | 2.1% |
| τ²-bench Airline | — | 72% |
| τ²-bench Banking | — | 25.3% |
| τ²-bench Retail | — | 72.4% |
| τ²-bench Telecom | — | 84.9% |
| Cybench | — | 60% |
| DeepResearch Bench | — | 52.6% |
| OSWorld | — | 62.9% |
| LMArena Search | — | 1159 |
| METR Time Horizons | — | 67.4% |
| Vending-Bench 2 | — | 3,839 |

## Reasoning

- Amazon Nova Lite: 19.3 (#260)
- Claude Sonnet 4.5: 26.9 (#125)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1462 |
| ARC-AGI-2 | — | 13.6% |
| SimpleBench | — | 54.3% |
| Kagi LLM Benchmark | — | 57.9% |
| NYT Connections (extended) | — | 37.3% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 6% |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 83.2% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 38.8% |
| Epoch Capabilities Index | — | 146.84 |
| ForecastBench | — | 61.9 |
| LiveBench | 36.4% | — |

## Math

- Amazon Nova Lite: 27.8 (#247)
- Claude Sonnet 4.5: 32.3 (#216)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| Omni-MATH | 23.3% | 55.3% |
| LMArena Math | 1227 | 1449 |
| FrontierMath (Tiers 1-3) | — | 23.9% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| ProofBench | — | 19% |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 97.7% |
| FrontierMath (Feb 2025 set) | — | 15.2% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Amazon Nova Lite: 26.3 (#259)
- Claude Sonnet 4.5: 48.4 (#76)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| Humanity's Last Exam | 3.6% | 13.7% |
| MMLU-Pro | 60% | 86.9% |
| Vectara Hallucination Rate | 6.1% | 12% |
| GPQA (HELM) | 39.7% | 68.6% |
| LMArena Expert | 1201 | 1482 |
| GPQA Diamond | — | 82.3% |
| SimpleQA Verified | — | 30.7% |
| MMLU | 77% | — |

## Multimodal

- Amazon Nova Lite: 25.5 (#123)
- Claude Sonnet 4.5: 34.8 (#89)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Vision | 990 | — |
| VPCT | — | 39.8% |
| LMArena Document | — | 1450 |

## Multilingual

- Amazon Nova Lite: 38.0 (#232)
- Claude Sonnet 4.5: 53.4 (#69)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Non-English | 1208 | 1425 |
| LMArena Chinese | 1225 | 1459 |
| LMArena French | 1237 | 1458 |
| LMArena German | 1229 | 1427 |
| LMArena Japanese | 1153 | 1390 |
| LMArena Korean | 1153 | 1403 |
| LMArena Russian | 1216 | 1437 |
| LMArena Spanish | 1226 | 1457 |

## Instruction Following

- Amazon Nova Lite: 59.3 (#255)
- Claude Sonnet 4.5: 75.0 (#78)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| IFEval | 77.6% | 85% |
| LMArena Instruction Following | 1205 | 1459 |
| LiveBench Instruction Following | 54.1% | — |

## Long Context

- Amazon Nova Lite: 37.4 (#217)
- Claude Sonnet 4.5: 45.2 (#46)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Longer Query | 1234 | 1476 |

## Writing & Preference

- Amazon Nova Lite: 42.1 (#237)
- Claude Sonnet 4.5: 66.5 (#34)

| Benchmark | Amazon Nova Lite | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Text | 1229 | 1439 |
| LMArena Creative Writing | 1197 | 1442 |
| WildBench | 75% | 85.4% |
| LMArena Multi-Turn | 1199 | 1465 |
| EQ-Bench Creative Writing | — | 1678 |
| LiveBench Language | 25.9% | — |

## FAQ

### Is Amazon Nova Lite better than Claude Sonnet 4.5?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index. Amazon Nova Lite costs 57× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Lite or Claude Sonnet 4.5?

Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Amazon Nova Lite or Claude Sonnet 4.5 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 32.5 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Amazon Nova Lite and Claude Sonnet 4.5 share?

25 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Claude Sonnet 4.5 has 73.