Model comparison
Amazon Nova Lite vs Llama 3-70B
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. Amazon Nova Lite scores higher in 5 categories and Llama 3-70B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Lite leads 27.8 to 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Llama 3-70B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.9 | 28.8 |
| Released | 2024-12-03 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Amazon Nova Lite: 32.5 (#270), Llama 3-70B: 35.8 (#218)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1239 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| LiveBench Coding | 27.5% | — |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 236.25 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Amazon Nova Lite leads
Amazon Nova Lite: 19.3 (#260), Llama 3-70B: 18.0 (#288)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 54.2% |
| LiveBench Data Analysis | 37.2% | — |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| LiveBench | 36.4% | — |
| WinoGrande | — | 83.5% |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), Llama 3-70B: 12.8 (#305)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Math | 1227 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 22.6% |
Knowledge Amazon Nova Lite leads
Amazon Nova Lite: 26.3 (#259), Llama 3-70B: 20.8 (#277)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1201 | 1149 |
| MMLU | 77% | 79.3% |
| GPQA Diamond | — | 40.6% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Llama 3-70B: —
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Amazon Nova Lite leads
Amazon Nova Lite: 38.0 (#232), Llama 3-70B: 33.6 (#251)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1208 | 1142 |
| LMArena Chinese | 1225 | 1114 |
| LMArena French | 1237 | 1232 |
| LMArena German | 1229 | 1169 |
| LMArena Japanese | 1153 | 1017 |
| LMArena Korean | 1153 | 1017 |
| LMArena Russian | 1216 | 1159 |
| LMArena Spanish | 1226 | 1241 |
Instruction Following Llama 3-70B leads
Amazon Nova Lite: 59.3 (#255), Llama 3-70B: 62.5 (#238)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1205 | 1194 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#217), Llama 3-70B: 35.6 (#240)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1234 | 1174 |
Writing & Preference Too close to call
Amazon Nova Lite: 42.1 (#237), Llama 3-70B: 42.8 (#231)
| Benchmark | Amazon Nova Lite | Llama 3-70B |
|---|---|---|
| LMArena Text | 1229 | 1221 |
| LMArena Creative Writing | 1197 | 1210 |
| LMArena Multi-Turn | 1199 | 1223 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Llama 3-70B?
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 28.8 on the Noometry Index.
Is Amazon Nova Lite or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 32.5 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and Llama 3-70B share?
18 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Llama 3-70B has 31.