# Amazon Nova Lite vs Llama 3.2 3B

> Amazon Nova Lite is the stronger model overall, scoring 31.9 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-llama-3-2-3b
- Last updated: 2026-10-11
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Amazon Nova Lite scores higher in 5 categories and Llama 3.2 3B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Lite leads 42.1 to 24.7.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
- Amazon Nova Lite accepts more context: 300K tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.9 | 28.9 |
| Rank | 265 | 321 |
| Context | 300K | 131K |
| Input $/M | $0.06 | $0.05 |
| Output $/M | $0.24 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Lite: 32.5 (#270)
- Llama 3.2 3B: 27.6 (#319)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1239 | 1098 |
| BigCodeBench Instruct | — | 23.4% |
| LiveBench Coding | 27.5% | — |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 236.25 | — |

## Agentic & Tool Use

- Amazon Nova Lite: —
- Llama 3.2 3B: 20.1 (#143)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |

## Reasoning

- Amazon Nova Lite: 19.3 (#260)
- Llama 3.2 3B: 21.0 (#228)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1095 |
| LiveBench Reasoning | 36.7% | — |
| LiveBench Data Analysis | 37.2% | — |
| LiveBench | 36.4% | — |

## Math

- Amazon Nova Lite: 27.8 (#247)
- Llama 3.2 3B: 32.4 (#214)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1227 | 1126 |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |

## Knowledge

- Amazon Nova Lite: 26.3 (#259)
- Llama 3.2 3B: 29.7 (#235)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1201 | 1090 |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |

## Multimodal

- Amazon Nova Lite: 25.5 (#123)
- Llama 3.2 3B: —

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 990 | — |

## Multilingual

- Amazon Nova Lite: 38.0 (#232)
- Llama 3.2 3B: 26.2 (#281)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1208 | 1019 |
| LMArena Chinese | 1225 | 1017 |
| LMArena German | 1229 | 1056 |
| LMArena Russian | 1216 | 949 |
| LMArena French | 1237 | — |
| LMArena Japanese | 1153 | — |
| LMArena Korean | 1153 | — |
| LMArena Spanish | 1226 | — |

## Instruction Following

- Amazon Nova Lite: 59.3 (#255)
- Llama 3.2 3B: 56.0 (#275)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1205 | 1089 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |

## Long Context

- Amazon Nova Lite: 37.4 (#217)
- Llama 3.2 3B: 33.4 (#261)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1234 | 1100 |

## Writing & Preference

- Amazon Nova Lite: 42.1 (#237)
- Llama 3.2 3B: 24.7 (#307)

| Benchmark | Amazon Nova Lite | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1229 | 1110 |
| LMArena Creative Writing | 1197 | 1094 |
| LMArena Multi-Turn | 1199 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |

## FAQ

### Is Amazon Nova Lite better than Llama 3.2 3B?

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 28.9 on the Noometry Index.

### Which is cheaper, Amazon Nova Lite or Llama 3.2 3B?

Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.

### Is Amazon Nova Lite or Llama 3.2 3B better for coding?

Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Lite does, with 300K tokens against 131K.

### How many benchmarks do Amazon Nova Lite and Llama 3.2 3B share?

13 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Llama 3.2 3B has 18.