Model comparison
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.
Last verified . 31 shared benchmarks.
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.
Side by side
| Amazon Nova Lite | Claude 3.7 Sonnet | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.9 | 39.5 |
| Released | 2024-12-03 | 2025-02-24 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 58 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
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 Not comparable
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 Too close to call
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 Claude 3.7 Sonnet leads
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 Claude 3.7 Sonnet leads
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 Claude 3.7 Sonnet leads
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 Claude 3.7 Sonnet leads
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 Claude 3.7 Sonnet leads
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 Claude 3.7 Sonnet leads
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 Claude 3.7 Sonnet leads
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 |
Frequently asked questions
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.