# Llama 3.2 1B vs StarCoder 2 3B

> Llama 3.2 1B has enough public results to be ranked (#349); StarCoder 2 3B does not yet, so treat this comparison as directional.

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

## Summary

- They share 2 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 3B leads 32.9 to 20.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 21.4% for StarCoder 2 3B.

## Snapshot

| | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 19.9 | 35.8 |
| Rank | 349 | — |
| Context | 60K | — |
| Input $/M | $0.027 | — |
| Output $/M | $0.20 | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 20.6 (#333)
- StarCoder 2 3B: 32.9

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 11.3% | 21.4% |
| BigCodeBench Instruct | 8.2% | — |
| LMArena Coding | 1071 | — |
| HumanEval+ | — | 27.4% |

## Agentic & Tool Use

- Llama 3.2 1B: 14.5 (#142)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 15.6 (#304)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 101.95 | 88.01 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1044 | — |
| WinoGrande | — | 57.1% |

## Math

- Llama 3.2 1B: 9.7 (#308)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LMArena Math | 1086 | — |
| GSM8K | — | 21.6% |

## Knowledge

- Llama 3.2 1B: 7.2 (#307)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 23.9% | — |
| LMArena Expert | 1007 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |

## Multilingual

- Llama 3.2 1B: 23.9 (#287)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 973 | — |
| LMArena Chinese | 958 | — |
| LMArena German | 1014 | — |
| LMArena Russian | 941 | — |

## Instruction Following

- Llama 3.2 1B: 52.6 (#285)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1031 | — |

## Long Context

- Llama 3.2 1B: 31.9 (#269)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1050 | — |

## Writing & Preference

- Llama 3.2 1B: 21.4 (#305)
- StarCoder 2 3B: —

| Benchmark | Llama 3.2 1B | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1055 | — |
| LMArena Creative Writing | 1033 | — |
| EQ-Bench Creative Writing | 200 | — |
| LMArena Multi-Turn | 1030 | — |

## FAQ

### Is Llama 3.2 1B better than StarCoder 2 3B?

Llama 3.2 1B has enough public results to be ranked (#349); StarCoder 2 3B does not yet, so treat this comparison as directional.

### Is Llama 3.2 1B or StarCoder 2 3B better for coding?

StarCoder 2 3B scores higher on coding benchmarks: 32.9 versus 20.6 in the Noometry coding category.

### How many benchmarks do Llama 3.2 1B and StarCoder 2 3B share?

2 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and StarCoder 2 3B has 7.