# Llama 3.2 1B vs Llama 3-70B

> Llama 3-70B is the stronger model overall, scoring 28.8 to 20.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-1b-vs-llama-3-70b
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Llama 3-70B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-70B leads 42.8 to 21.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 54.5% for Llama 3-70B.

## Snapshot

| | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 20.1 | 28.8 |
| Rank | 354 | 323 |
| Context | 60K | — |
| Input $/M | $0.027 | — |
| Output $/M | $0.20 | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 21.1 (#338)
- Llama 3-70B: 35.8 (#218)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 8.2% | 43.6% |
| LMArena Coding | 1070 | 1206 |
| BigCodeBench Complete | 11.3% | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |

## Agentic & Tool Use

- Llama 3.2 1B: 14.6 (#150)
- Llama 3-70B: 21.1 (#139)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| Cybench | — | 5% |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 16.2 (#308)
- Llama 3-70B: 18.0 (#288)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1195 |
| Epoch Capabilities Index | 101.99 | 122.93 |
| Kagi LLM Benchmark | — | 35.1% |
| Chess Puzzles | 0% | — |
| DTBench | — | 54.2% |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |

## Math

- Llama 3.2 1B: 10.4 (#313)
- Llama 3-70B: 12.8 (#305)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 4.3% |
| LMArena Math | 1086 | 1218 |
| MATH Level 5 | — | 22.6% |

## Knowledge

- Llama 3.2 1B: 7.2 (#312)
- Llama 3-70B: 20.8 (#277)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 23.9% | 40.6% |
| LMArena Expert | 1007 | 1149 |
| MMLU | — | 79.3% |

## Multilingual

- Llama 3.2 1B: 23.8 (#292)
- Llama 3-70B: 33.6 (#251)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 973 | 1142 |
| LMArena Chinese | 959 | 1114 |
| LMArena German | 1014 | 1169 |
| LMArena Russian | 941 | 1159 |
| LMArena French | — | 1232 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Spanish | — | 1241 |

## Instruction Following

- Llama 3.2 1B: 52.4 (#290)
- Llama 3-70B: 62.5 (#238)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1194 |

## Long Context

- Llama 3.2 1B: 31.9 (#274)
- Llama 3-70B: 35.6 (#240)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1050 | 1174 |

## Writing & Preference

- Llama 3.2 1B: 21.3 (#310)
- Llama 3-70B: 42.8 (#231)

| Benchmark | Llama 3.2 1B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1055 | 1221 |
| LMArena Creative Writing | 1033 | 1210 |
| LMArena Multi-Turn | 1030 | 1223 |
| EQ-Bench Creative Writing | 200 | — |

## FAQ

### Is Llama 3.2 1B better than Llama 3-70B?

Llama 3-70B is the stronger model overall, scoring 28.8 to 20.1 on the Noometry Index.

### Is Llama 3.2 1B or Llama 3-70B better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.8 versus 21.1 in the Noometry coding category.

### How many benchmarks do Llama 3.2 1B and Llama 3-70B share?

18 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Llama 3-70B has 31.