Model comparison
Amazon Nova Lite vs Claude 3.5 Haiku
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.2 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 3 categories and Claude 3.5 Haiku in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Lite leads 27.8 to 14.7.
- The biggest single-benchmark swing is LiveBench Coding: 27.5% for Amazon Nova Lite and 51.4% for Claude 3.5 Haiku.
Side by side
| Amazon Nova Lite | Claude 3.5 Haiku | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.9 | 29.2 |
| Released | 2024-12-03 | 2024-10-22 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Lite: 32.5 (#270), Claude 3.5 Haiku: 32.9 (#265)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LiveBench Coding | 27.5% | 51.4% |
| LMArena Coding | 1239 | 1286 |
| Aider Polyglot | — | 28% |
| SciCode | — | 27.4% |
| WeirdML | — | 30.7% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 59% |
| CadEval | — | 32% |
| ALE-Bench | 236.25 | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, Claude 3.5 Haiku: 28.0 (#95)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| BALROG | — | 19.3% |
Reasoning Amazon Nova Lite leads
Amazon Nova Lite: 19.3 (#260), Claude 3.5 Haiku: 17.7 (#290)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LiveBench Reasoning | 36.7% | 28.1% |
| LMArena Hard Prompts | 1220 | 1251 |
| LiveBench Data Analysis | 37.2% | 48.5% |
| LiveBench | 36.4% | 43.5% |
| CritPt | — | 0% |
| DTBench | — | 56.7% |
| Epoch Capabilities Index | — | 127.15 |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), Claude 3.5 Haiku: 14.7 (#300)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| Omni-MATH | 23.3% | 22.4% |
| LiveBench Math | 36.7% | 35.5% |
| LMArena Math | 1227 | 1244 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 46.4% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Amazon Nova Lite leads
Amazon Nova Lite: 26.3 (#259), Claude 3.5 Haiku: 18.7 (#281)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| MMLU-Pro | 60% | 60.5% |
| GPQA (HELM) | 39.7% | 36.3% |
| LMArena Expert | 1201 | 1208 |
| MMLU | 77% | 74.3% |
| GPQA Diamond | — | 38.1% |
| Humanity's Last Exam | 3.6% | — |
| Confabulations | — | 36.7% |
| Vectara Hallucination Rate | 6.1% | — |
Multimodal Claude 3.5 Haiku leads
Amazon Nova Lite: 25.5 (#123), Claude 3.5 Haiku: 26.8 (#117)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LMArena Vision | 990 | 1092 |
| GeoBench | — | 34% |
Multilingual Claude 3.5 Haiku leads
Amazon Nova Lite: 38.0 (#232), Claude 3.5 Haiku: 40.0 (#218)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LMArena Non-English | 1208 | 1238 |
| LMArena Chinese | 1225 | 1229 |
| LMArena French | 1237 | 1264 |
| LMArena German | 1229 | 1237 |
| LMArena Japanese | 1153 | 1175 |
| LMArena Korean | 1153 | 1173 |
| LMArena Russian | 1216 | 1253 |
| LMArena Spanish | 1226 | 1261 |
Instruction Following Claude 3.5 Haiku leads
Amazon Nova Lite: 59.3 (#255), Claude 3.5 Haiku: 62.9 (#234)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LiveBench Instruction Following | 54.1% | 61.9% |
| IFEval | 77.6% | 79.2% |
| LMArena Instruction Following | 1205 | 1241 |
Long Context Too close to call
Amazon Nova Lite: 37.4 (#217), Claude 3.5 Haiku: 38.3 (#200)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LMArena Longer Query | 1234 | 1261 |
Writing & Preference Too close to call
Amazon Nova Lite: 42.1 (#237), Claude 3.5 Haiku: 42.7 (#234)
| Benchmark | Amazon Nova Lite | Claude 3.5 Haiku |
|---|---|---|
| LMArena Text | 1229 | 1255 |
| LMArena Creative Writing | 1197 | 1233 |
| WildBench | 75% | 76% |
| LMArena Multi-Turn | 1199 | 1265 |
| LiveBench Language | 25.9% | 35.4% |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | — | 1146 |
Frequently asked questions
Is Amazon Nova Lite better than Claude 3.5 Haiku?
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.2 on the Noometry Index.
Is Amazon Nova Lite or Claude 3.5 Haiku better for coding?
They score almost the same on coding (32.5 vs 32.9); test both on your own repository before choosing.
How many benchmarks do Amazon Nova Lite and Claude 3.5 Haiku share?
31 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Claude 3.5 Haiku has 49.