# Qwen2.5-Coder-32B vs Qwen3-4B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-coder-32b-vs-qwen3-4b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Snapshot

| | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 32.9 | 31.5 |
| Rank | 239 | 261 |
| Context | 33K | — |
| Input $/M | $0.66 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- Qwen2.5-Coder-32B: 22.4 (#328)
- Qwen3-4B: —

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| LMArena Coding | 1276 | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |

## Agentic & Tool Use

- Qwen2.5-Coder-32B: —
- Qwen3-4B: 27.3 (#94)

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |

## Reasoning

- Qwen2.5-Coder-32B: 20.4 (#220)
- Qwen3-4B: 18.5 (#264)

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 42.1% | — |
| LMArena Hard Prompts | 1251 | — |
| LiveBench Data Analysis | 49.9% | — |
| Epoch Capabilities Index | 119.41 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |

## Math

- Qwen2.5-Coder-32B: 30.8 (#203)
- Qwen3-4B: 28.5 (#228)

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LiveBench Math | 46.6% | — |
| LMArena Math | 1251 | — |
| GSM8K | 93% | — |

## Knowledge

- Qwen2.5-Coder-32B: 32.9 (#200)
- Qwen3-4B: 33.0 (#198)

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1221 | — |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |

## Multilingual

- Qwen2.5-Coder-32B: 38.0 (#230)
- Qwen3-4B: —

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1222 | — |
| LMArena Russian | 1228 | — |

## Instruction Following

- Qwen2.5-Coder-32B: 61.6 (#240)
- Qwen3-4B: —

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| LiveBench Instruction Following | 58.7% | — |
| LMArena Instruction Following | 1223 | — |

## Long Context

- Qwen2.5-Coder-32B: 37.9 (#204)
- Qwen3-4B: —

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1251 | — |

## Writing & Preference

- Qwen2.5-Coder-32B: 41.8 (#235)
- Qwen3-4B: —

| Benchmark | Qwen2.5-Coder-32B | Qwen3-4B |
|---|---|---|
| LMArena Text | 1230 | — |
| LMArena Creative Writing | 1174 | — |
| LMArena Multi-Turn | 1222 | — |
| LiveBench Language | 23.3% | — |

## FAQ

### Is Qwen2.5-Coder-32B better than Qwen3-4B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 31.5 on the Noometry Index.

### How many benchmarks do Qwen2.5-Coder-32B and Qwen3-4B share?

0 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Qwen3-4B has 6.