# Amazon Nova Pro vs Llama 4 Maverick

> Amazon Nova Pro and Llama 4 Maverick score almost the same on the Noometry Index (30.5 vs 30.6), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-llama-4-maverick
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Amazon Nova Pro scores higher in 5 categories and Llama 4 Maverick in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Llama 4 Maverick leads 27.9 to 16.6.
- The biggest single-benchmark swing is GPQA (HELM): 44.6% for Amazon Nova Pro and 65% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 30.5 | 30.6 |
| Rank | 278 | 276 |
| Context | 300K | 128K |
| Input $/M | $0.80 | $0.19 |
| Output $/M | $3.20 | $0.65 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- Llama 4 Maverick: 26.3 (#318)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1270 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- Llama 4 Maverick: 27.9 (#86)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 37.3% |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- Llama 4 Maverick: 10.1 (#337)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1281 |
| Epoch Capabilities Index | 123.75 | 132.2 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 61.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 15.9% |
| ForecastBench | — | 57.5 |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 26.4 (#240)
- Llama 4 Maverick: 24.6 (#256)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| Omni-MATH | 24.2% | 42.2% |
| LMArena Math | 1252 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- Llama 4 Maverick: 33.3 (#196)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| Humanity's Last Exam | 4.4% | 5.7% |
| MMLU-Pro | 67.3% | 81% |
| Confabulations | 30.1% | 22.6% |
| Vectara Hallucination Rate | 5.1% | 8.2% |
| GPQA (HELM) | 44.6% | 65% |
| LMArena Expert | 1211 | 1259 |
| GPQA Diamond | — | 67% |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 24.5 (#121)
- Llama 4 Maverick: 30.9 (#100)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 980 | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- Llama 4 Maverick: 42.4 (#190)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1234 | 1269 |
| LMArena Chinese | 1244 | 1277 |
| LMArena French | 1270 | 1258 |
| LMArena German | 1243 | 1291 |
| LMArena Japanese | 1200 | 1207 |
| LMArena Korean | 1203 | 1203 |
| LMArena Russian | 1240 | 1286 |
| LMArena Spanish | 1182 | 1293 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- Llama 4 Maverick: 71.9 (#140)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| IFEval | 81.5% | 90.8% |
| LMArena Instruction Following | 1235 | 1267 |
| LiveBench Instruction Following | 67.1% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- Llama 4 Maverick: 31.4 (#274)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1255 | 1280 |
| Fiction.LiveBench | — | 46.2% |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- Llama 4 Maverick: 39.0 (#247)

| Benchmark | Amazon Nova Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1259 | 1287 |
| LMArena Creative Writing | 1212 | 1266 |
| Short-Story Creative Writing | 60.5% | 62% |
| WildBench | 77.7% | 80% |
| LMArena Multi-Turn | 1245 | 1289 |
| EQ-Bench Creative Writing | — | 860 |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Llama 4 Maverick?

Amazon Nova Pro and Llama 4 Maverick score almost the same on the Noometry Index (30.5 vs 30.6), so choose on price, context window or the category you care about most.

### Which is cheaper, Amazon Nova Pro or Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or Llama 4 Maverick better for coding?

Amazon Nova Pro scores higher on coding benchmarks: 34.6 versus 26.3 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 128K.

### How many benchmarks do Amazon Nova Pro and Llama 4 Maverick share?

29 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 4 Maverick has 54.