Model comparison
Amazon Nova Lite vs Llama 3.1-405B
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 30.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Amazon Nova Lite scores higher in 3 categories and Llama 3.1-405B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Lite leads 27.8 to 18.4.
- The biggest single-benchmark swing is GPQA (HELM): 39.7% for Amazon Nova Lite and 52.2% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Llama 3.1-405B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.9 | 30.7 |
| Released | 2024-12-03 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 42 |
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), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1239 | 1291 |
| WeirdML | — | 21.4% |
| LiveBench Coding | 27.5% | — |
| ALE-Bench | 236.25 | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, Llama 3.1-405B: 21.0 (#140)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Amazon Nova Lite leads
Amazon Nova Lite: 19.3 (#260), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1269 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 61.4% |
| LiveBench Data Analysis | 37.2% | — |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.75 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| LiveBench | 36.4% | — |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| Omni-MATH | 23.3% | 24.9% |
| LMArena Math | 1227 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 49.8% |
Knowledge Llama 3.1-405B leads
Amazon Nova Lite: 26.3 (#259), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| MMLU-Pro | 60% | 72.3% |
| GPQA (HELM) | 39.7% | 52.2% |
| LMArena Expert | 1201 | 1243 |
| MMLU | 77% | 84.5% |
| GPQA Diamond | — | 50.9% |
| Humanity's Last Exam | 3.6% | — |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 6.1% | — |
| ARC (AI2) Challenge | — | 95.3% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Llama 3.1-405B: —
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Llama 3.1-405B leads
Amazon Nova Lite: 38.0 (#232), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1208 | 1248 |
| LMArena Chinese | 1225 | 1242 |
| LMArena French | 1237 | 1279 |
| LMArena German | 1229 | 1252 |
| LMArena Japanese | 1153 | 1208 |
| LMArena Korean | 1153 | 1184 |
| LMArena Russian | 1216 | 1265 |
| LMArena Spanish | 1226 | 1260 |
Instruction Following Llama 3.1-405B leads
Amazon Nova Lite: 59.3 (#255), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| IFEval | 77.6% | 81.1% |
| LMArena Instruction Following | 1205 | 1259 |
| LiveBench Instruction Following | 54.1% | — |
Long Context Llama 3.1-405B leads
Amazon Nova Lite: 37.4 (#217), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1234 | 1266 |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.1 (#237), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Amazon Nova Lite | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1229 | 1284 |
| LMArena Creative Writing | 1197 | 1262 |
| WildBench | 75% | 78.3% |
| LMArena Multi-Turn | 1199 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Llama 3.1-405B?
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 30.7 on the Noometry Index.
Is Amazon Nova Lite or Llama 3.1-405B better for coding?
They score almost the same on coding (32.5 vs 33.1); test both on your own repository before choosing.
How many benchmarks do Amazon Nova Lite and Llama 3.1-405B share?
23 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Llama 3.1-405B has 42.