# Llama 3.1-8B vs Llama 3.2 1B

> Llama 3.1-8B is the stronger model overall, scoring 23.0 to 20.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-8b-vs-llama-3-2-1b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Llama 3.1-8B scores higher in 6 categories and Llama 3.2 1B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 3.1-8B leads 34.0 to 23.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 40.5% for Llama 3.1-8B and 11.3% for Llama 3.2 1B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.027 / $0.20 for Llama 3.2 1B.
- Llama 3.1-8B accepts more context: 128K tokens versus 60K.

## Snapshot

| | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 23.0 | 20.1 |
| Rank | 352 | 354 |
| Context | 128K | 60K |
| Input $/M | $0.05 | $0.027 |
| Output $/M | $0.08 | $0.20 |
| Weights | Open | Open |

## Coding

- Llama 3.1-8B: 20.2 (#340)
- Llama 3.2 1B: 21.1 (#338)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| BigCodeBench Instruct | 32.8% | 8.2% |
| LMArena Coding | 1195 | 1070 |
| BigCodeBench Complete | 40.5% | 11.3% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |

## Agentic & Tool Use

- Llama 3.1-8B: 22.5 (#131)
- Llama 3.2 1B: 14.6 (#150)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | 10.8% |
| BALROG | 15.1% | 6.6% |

## Reasoning

- Llama 3.1-8B: 14.9 (#321)
- Llama 3.2 1B: 16.2 (#308)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1175 | 1044 |
| Epoch Capabilities Index | 116.57 | 101.99 |
| CritPt | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| PIQA | 81.2% | — |

## Math

- Llama 3.1-8B: 10.2 (#317)
- Llama 3.2 1B: 10.4 (#313)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 0.6% |
| LMArena Math | 1179 | 1086 |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |

## Knowledge

- Llama 3.1-8B: 8.0 (#307)
- Llama 3.2 1B: 7.2 (#312)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 27% | 23.9% |
| LMArena Expert | 1144 | 1007 |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |

## Multilingual

- Llama 3.1-8B: 34.0 (#249)
- Llama 3.2 1B: 23.8 (#292)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1148 | 973 |
| LMArena Chinese | 1151 | 959 |
| LMArena German | 1144 | 1014 |
| LMArena Russian | 1158 | 941 |
| LMArena French | 1177 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1053 | — |
| LMArena Spanish | 1169 | — |

## Instruction Following

- Llama 3.1-8B: 58.9 (#258)
- Llama 3.2 1B: 52.4 (#290)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1159 | 1031 |
| IFEval | 74.3% | — |

## Long Context

- Llama 3.1-8B: 35.8 (#238)
- Llama 3.2 1B: 31.9 (#274)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1182 | 1050 |

## Writing & Preference

- Llama 3.1-8B: 29.7 (#290)
- Llama 3.2 1B: 21.3 (#310)

| Benchmark | Llama 3.1-8B | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1187 | 1055 |
| LMArena Creative Writing | 1154 | 1033 |
| EQ-Bench Creative Writing | 713 | 200 |
| LMArena Multi-Turn | 1172 | 1030 |
| WildBench | 68.7% | — |

## FAQ

### Is Llama 3.1-8B better than Llama 3.2 1B?

Llama 3.1-8B is the stronger model overall, scoring 23.0 to 20.1 on the Noometry Index.

### Which is cheaper, Llama 3.1-8B or Llama 3.2 1B?

Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Llama 3.2 1B lists at $0.027 and $0.20.

### Is Llama 3.1-8B or Llama 3.2 1B better for coding?

They score almost the same on coding (20.2 vs 21.1); test both on your own repository before choosing.

### Which has the bigger context window?

Llama 3.1-8B does, with 128K tokens against 60K.

### How many benchmarks do Llama 3.1-8B and Llama 3.2 1B share?

22 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Llama 3.2 1B has 22.