# Llama 3.2 3B vs Qwen2.5-Coder (1.5B)

> Llama 3.2 3B has enough public results to be ranked (#318); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-3-2-3b-vs-qwen2-5-coder
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Snapshot

| | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.4 | — |
| Rank | 318 | — |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.33 | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 3B: 27.1 (#314)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| BigCodeBench Instruct | 23.4% | — |
| LMArena Coding | 1098 | — |
| BigCodeBench Complete | 28.3% | — |

## Agentic & Tool Use

- Llama 3.2 3B: 19.9 (#135)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |

## Reasoning

- Llama 3.2 3B: 20.1 (#225)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Hard Prompts | 1095 | — |
| Epoch Capabilities Index | — | 112.93 |
| HellaSwag | — | 76.8% |
| WinoGrande | — | 72.9% |

## Math

- Llama 3.2 3B: 29.9 (#213)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Math | 1126 | — |
| GSM8K | — | 86.7% |

## Knowledge

- Llama 3.2 3B: 29.1 (#232)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Expert | 1090 | — |
| ARC (AI2) Challenge | — | 60.9% |
| MMLU | — | 68% |

## Multilingual

- Llama 3.2 3B: 26.4 (#276)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Non-English | 1019 | — |
| LMArena Chinese | 1017 | — |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |

## Instruction Following

- Llama 3.2 3B: 56.3 (#270)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Instruction Following | 1089 | — |

## Long Context

- Llama 3.2 3B: 33.4 (#256)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Longer Query | 1101 | — |

## Writing & Preference

- Llama 3.2 3B: 24.9 (#302)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Llama 3.2 3B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1094 | — |
| EQ-Bench Creative Writing | 595 | — |
| LMArena Multi-Turn | 1105 | — |

## FAQ

### Is Llama 3.2 3B better than Qwen2.5-Coder (1.5B)?

Llama 3.2 3B has enough public results to be ranked (#318); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

### How many benchmarks do Llama 3.2 3B and Qwen2.5-Coder (1.5B) share?

0 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Qwen2.5-Coder (1.5B) has 6.