Model comparison
Amazon Nova Pro vs Llama 3.1-405B
Amazon Nova Pro and Llama 3.1-405B score almost the same on the Noometry Index (31.0 vs 30.7), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. Amazon Nova Pro scores higher in 4 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 Pro leads 28.5 to 18.4.
- The biggest single-benchmark swing is Confabulations: 30.1% for Amazon Nova Pro and 17.6% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Llama 3.1-405B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.0 | 30.7 |
| Released | 2024-12-03 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1270 | 1291 |
| WeirdML | — | 21.4% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Llama 3.1-405B leads
Amazon Nova Pro: 16.7 (#147), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | 1.7% | 7.4% |
| Berkeley Function Calling Leaderboard | 25% | — |
| Cybench | — | 7.5% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1269 |
| Epoch Capabilities Index | 123.8 | 128.75 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 61.4% |
| LiveBench Data Analysis | 48.3% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| LiveBench | 43.5% | — |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| Omni-MATH | 24.2% | 24.9% |
| LMArena Math | 1252 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 49.8% |
Knowledge Llama 3.1-405B leads
Amazon Nova Pro: 27.4 (#250), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| MMLU-Pro | 67.3% | 72.3% |
| Confabulations | 30.1% | 17.6% |
| GPQA (HELM) | 44.6% | 52.2% |
| LMArena Expert | 1211 | 1243 |
| MMLU | 82% | 84.5% |
| GPQA Diamond | — | 50.9% |
| Humanity's Last Exam | 4.4% | — |
| Vectara Hallucination Rate | 5.1% | — |
| ARC (AI2) Challenge | — | 95.3% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Llama 3.1-405B: —
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Too close to call
Amazon Nova Pro: 39.7 (#223), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1234 | 1248 |
| LMArena Chinese | 1244 | 1242 |
| LMArena French | 1271 | 1279 |
| LMArena German | 1243 | 1252 |
| LMArena Japanese | 1200 | 1208 |
| LMArena Korean | 1203 | 1184 |
| LMArena Russian | 1240 | 1265 |
| LMArena Spanish | 1182 | 1260 |
Instruction Following Llama 3.1-405B leads
Amazon Nova Pro: 64.9 (#226), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| IFEval | 81.5% | 81.1% |
| LMArena Instruction Following | 1235 | 1259 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1255 | 1266 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1259 | 1284 |
| LMArena Creative Writing | 1212 | 1262 |
| WildBench | 77.7% | 78.3% |
| LMArena Multi-Turn | 1246 | 1297 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 870 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Llama 3.1-405B?
Amazon Nova Pro and Llama 3.1-405B score almost the same on the Noometry Index (31.0 vs 30.7), so choose on price, context window or the category you care about most.
Is Amazon Nova Pro or Llama 3.1-405B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 33.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Llama 3.1-405B share?
26 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 3.1-405B has 42.