# Phi-4 Mini vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 30.4 on the Noometry Index. Phi-4 Mini costs 5.7× less per token, which makes it the better buy when Qwen2.5-Coder-32B's lead doesn't matter for your workload.

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

## Summary

- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 32.9 to 24.8.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Phi-4 Mini accepts more context: 128K tokens versus 33K.

## Snapshot

| | Phi-4 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.4 | 32.9 |
| Rank | 280 | 239 |
| Context | 128K | 33K |
| Input $/M | $0.075 | $0.66 |
| Output $/M | $0.30 | $1 |
| Weights | Open | Open |

## Coding

- Phi-4 Mini: 27.6 (#312)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | Phi-4 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| SciCode | 10.8% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| LMArena Coding | — | 1276 |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- Phi-4 Mini: 21.7 (#190)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | Phi-4 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| CritPt | 0% | — |
| 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

- Phi-4 Mini: —
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | Phi-4 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | — | 46.6% |
| LMArena Math | — | 1251 |
| GSM8K | — | 93% |

## Knowledge

- Phi-4 Mini: 24.8 (#261)
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | Phi-4 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

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

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

## Instruction Following

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

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

## Long Context

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

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

## Writing & Preference

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

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

## FAQ

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

Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 30.4 on the Noometry Index. Phi-4 Mini costs 5.7× less per token, which makes it the better buy when Qwen2.5-Coder-32B's lead doesn't matter for your workload.

### Which is cheaper, Phi-4 Mini or Qwen2.5-Coder-32B?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

### Is Phi-4 Mini or Qwen2.5-Coder-32B better for coding?

Phi-4 Mini scores higher on coding benchmarks: 27.6 versus 22.4 in the Noometry coding category.

### Which has the bigger context window?

Phi-4 Mini does, with 128K tokens against 33K.

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

0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen2.5-Coder-32B has 31.