# Llama 3.2 3B vs Qwen2.5 32B Instruct

> Qwen2.5 32B Instruct is the stronger model overall, scoring 30.1 to 28.9 on the Noometry Index. Llama 3.2 3B costs 10× less per token, which makes it the better buy when Qwen2.5 32B Instruct's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-3-2-3b-vs-qwen2-5-32b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Llama 3.2 3B scores higher in 3 categories and Qwen2.5 32B Instruct in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.2 3B leads 32.4 to 16.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 52.3% for Qwen2.5 32B Instruct.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.

## Snapshot

| | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.9 | 30.1 |
| Rank | 321 | 297 |
| Context | 131K | 131K |
| Input $/M | $0.05 | $0.70 |
| Output $/M | $0.33 | $2.80 |
| Weights | Open | Open |

## Coding

- Llama 3.2 3B: 27.6 (#319)
- Qwen2.5 32B Instruct: 38.7 (#169)

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | 23.4% | 45% |
| BigCodeBench Complete | 28.3% | 52.3% |
| LMArena Coding | 1098 | — |

## Agentic & Tool Use

- Llama 3.2 3B: 20.1 (#143)
- Qwen2.5 32B Instruct: —

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |

## Reasoning

- Llama 3.2 3B: 21.0 (#228)
- Qwen2.5 32B Instruct: 19.2 (#266)

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1095 | — |
| Epoch Capabilities Index | — | 128.52 |

## Math

- Llama 3.2 3B: 32.4 (#214)
- Qwen2.5 32B Instruct: 16.2 (#296)

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| LMArena Math | 1126 | — |
| MATH Level 5 | — | 56.1% |

## Knowledge

- Llama 3.2 3B: 29.7 (#235)
- Qwen2.5 32B Instruct: 24.9 (#266)

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| LMArena Expert | 1090 | — |

## Multilingual

- Llama 3.2 3B: 26.2 (#281)
- Qwen2.5 32B Instruct: —

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1019 | — |
| LMArena Chinese | 1017 | — |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |

## Instruction Following

- Llama 3.2 3B: 56.0 (#275)
- Qwen2.5 32B Instruct: —

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1089 | — |

## Long Context

- Llama 3.2 3B: 33.4 (#261)
- Qwen2.5 32B Instruct: —

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1100 | — |

## Writing & Preference

- Llama 3.2 3B: 24.7 (#307)
- Qwen2.5 32B Instruct: —

| Benchmark | Llama 3.2 3B | Qwen2.5 32B Instruct |
|---|---|---|
| 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 32B Instruct?

Qwen2.5 32B Instruct is the stronger model overall, scoring 30.1 to 28.9 on the Noometry Index. Llama 3.2 3B costs 10× less per token, which makes it the better buy when Qwen2.5 32B Instruct's lead doesn't matter for your workload.

### Which is cheaper, Llama 3.2 3B or Qwen2.5 32B Instruct?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.

### Is Llama 3.2 3B or Qwen2.5 32B Instruct better for coding?

Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do Llama 3.2 3B and Qwen2.5 32B Instruct share?

2 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Qwen2.5 32B Instruct has 7.