Model comparison
Amazon Nova Lite vs Claude 3 Sonnet
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Amazon Nova Lite scores higher in 7 categories and Claude 3 Sonnet in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Lite leads 27.8 to 10.7.
Side by side
| Amazon Nova Lite | Claude 3 Sonnet | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.9 | 29.0 |
| Released | 2024-12-03 | 2024-02-29 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Lite leads
Amazon Nova Lite: 32.5 (#270), Claude 3 Sonnet: 29.6 (#302)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Coding | 1239 | 1223 |
| WeirdML | — | 10.2% |
| BigCodeBench Instruct | — | 42.7% |
| LiveBench Coding | 27.5% | — |
| BigCodeBench Complete | — | 53.8% |
| ALE-Bench | 236.25 | — |
| HumanEval+ | — | 64% |
| MBPP+ | — | 69.3% |
Reasoning Claude 3 Sonnet leads
Amazon Nova Lite: 19.3 (#260), Claude 3 Sonnet: 20.5 (#237)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1197 |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 53.6% |
| LiveBench Data Analysis | 37.2% | — |
| Epoch Capabilities Index | — | 120.7 |
| LiveBench | 36.4% | — |
| WinoGrande | — | 75.1% |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), Claude 3 Sonnet: 10.7 (#310)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Math | 1227 | 1213 |
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 18.2% |
Knowledge Amazon Nova Lite leads
Amazon Nova Lite: 26.3 (#259), Claude 3 Sonnet: 21.1 (#276)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Expert | 1201 | 1173 |
| MMLU | 77% | 75.9% |
| GPQA Diamond | — | 40.6% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
Multimodal Too close to call
Amazon Nova Lite: 25.5 (#123), Claude 3 Sonnet: 25.2 (#125)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Vision | 990 | 984 |
Multilingual Too close to call
Amazon Nova Lite: 38.0 (#232), Claude 3 Sonnet: 37.8 (#234)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Non-English | 1208 | 1205 |
| LMArena Chinese | 1225 | 1189 |
| LMArena French | 1237 | 1229 |
| LMArena German | 1229 | 1204 |
| LMArena Japanese | 1153 | 1131 |
| LMArena Korean | 1153 | 1128 |
| LMArena Russian | 1216 | 1227 |
| LMArena Spanish | 1226 | 1204 |
Instruction Following Claude 3 Sonnet leads
Amazon Nova Lite: 59.3 (#255), Claude 3 Sonnet: 62.8 (#235)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Instruction Following | 1205 | 1199 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Too close to call
Amazon Nova Lite: 37.4 (#217), Claude 3 Sonnet: 36.7 (#228)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Longer Query | 1234 | 1211 |
Writing & Preference Too close to call
Amazon Nova Lite: 42.1 (#237), Claude 3 Sonnet: 42.1 (#238)
| Benchmark | Amazon Nova Lite | Claude 3 Sonnet |
|---|---|---|
| LMArena Text | 1229 | 1218 |
| LMArena Creative Writing | 1197 | 1186 |
| LMArena Multi-Turn | 1199 | 1227 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Claude 3 Sonnet?
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.0 on the Noometry Index.
Is Amazon Nova Lite or Claude 3 Sonnet better for coding?
Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 29.6 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and Claude 3 Sonnet share?
19 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Claude 3 Sonnet has 30.