# 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.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-llama-3-1-405b
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- 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.

## Snapshot

| | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.0 | 30.7 |
| Rank | 281 | 288 |
| Context | 300K | — |
| Input $/M | $0.80 | — |
| Output $/M | $3.20 | — |
| Weights | Proprietary | Open |

## Coding

- 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

- 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: 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: 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

- 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

- Amazon Nova Pro: 25.0 (#126)
- Llama 3.1-405B: —

| Benchmark | Amazon Nova Pro | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- 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

- 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

- 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: 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% | — |

## FAQ

### 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.