# Llama 2-70B vs Llama 3.2 3B

> Llama 3.2 3B is the stronger model overall, scoring 28.4 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-70b-vs-llama-3-2-3b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Llama 2-70B scores higher in 3 categories and Llama 3.2 3B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.2 3B leads 29.9 to 7.5.

## Snapshot

| | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 24.1 | 28.4 |
| Rank | 343 | 318 |
| Context | — | 131K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.33 |
| Weights | Open | Open |

## Coding

- Llama 2-70B: 30.8 (#281)
- Llama 3.2 3B: 27.1 (#314)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1079 | 1098 |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |

## Agentic & Tool Use

- Llama 2-70B: —
- Llama 3.2 3B: 19.9 (#135)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |

## Reasoning

- Llama 2-70B: 13.7 (#324)
- Llama 3.2 3B: 20.1 (#225)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1095 |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.59 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |

## Math

- Llama 2-70B: 7.5 (#320)
- Llama 3.2 3B: 29.9 (#213)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1091 | 1126 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |

## Knowledge

- Llama 2-70B: 7.4 (#305)
- Llama 3.2 3B: 29.1 (#232)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1039 | 1090 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |

## Multilingual

- Llama 2-70B: 27.9 (#269)
- Llama 3.2 3B: 26.4 (#276)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1045 | 1019 |
| LMArena Chinese | 994 | 1017 |
| LMArena German | 1041 | 1056 |
| LMArena Russian | 1083 | 949 |
| LMArena French | 1089 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Spanish | 1142 | — |

## Instruction Following

- Llama 2-70B: 55.1 (#273)
- Llama 3.2 3B: 56.3 (#270)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1071 | 1089 |

## Long Context

- Llama 2-70B: 32.2 (#265)
- Llama 3.2 3B: 33.4 (#256)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1062 | 1101 |

## Writing & Preference

- Llama 2-70B: 32.5 (#274)
- Llama 3.2 3B: 24.9 (#302)

| Benchmark | Llama 2-70B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1115 | 1110 |
| LMArena Creative Writing | 1075 | 1094 |
| LMArena Multi-Turn | 1088 | 1105 |
| EQ-Bench Creative Writing | — | 595 |

## FAQ

### Is Llama 2-70B better than Llama 3.2 3B?

Llama 3.2 3B is the stronger model overall, scoring 28.4 to 24.1 on the Noometry Index.

### Is Llama 2-70B or Llama 3.2 3B better for coding?

Llama 2-70B scores higher on coding benchmarks: 30.8 versus 27.1 in the Noometry coding category.

### How many benchmarks do Llama 2-70B and Llama 3.2 3B share?

13 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Llama 3.2 3B has 18.