# Phi 3 Mini 128k Instruct vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-128k-instruct-vs-qwen2-5-coder-32b
- Last updated: 2026-10-11
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 1 category and Qwen2.5-Coder-32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Coder-32B leads 41.6 to 27.1.
- The biggest single-benchmark swing is BigCodeBench Instruct: 29.6% for Phi 3 Mini 128k Instruct and 49% for Qwen2.5-Coder-32B.

## Snapshot

| | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 33.4 |
| Rank | 305 | 245 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 128k Instruct: 28.8 (#312)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 29.6% | 49% |
| LMArena Coding | 1039 | 1276 |
| BigCodeBench Complete | 40.6% | 58% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LiveBench Coding | — | 56.9% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Reasoning

- Phi 3 Mini 128k Instruct: 19.6 (#256)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- Phi 3 Mini 128k Instruct: 31.6 (#222)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1089 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- Phi 3 Mini 128k Instruct: 26.8 (#254)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 984 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- Phi 3 Mini 128k Instruct: 25.2 (#285)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1000 | 1205 |
| LMArena Chinese | 1016 | 1222 |
| LMArena Russian | 1004 | 1228 |
| LMArena French | 1039 | — |
| LMArena German | 1006 | — |
| LMArena Japanese | 899 | — |
| LMArena Korean | 856 | — |
| LMArena Spanish | 1059 | — |

## Instruction Following

- Phi 3 Mini 128k Instruct: 51.8 (#294)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Phi 3 Mini 128k Instruct: 30.4 (#289)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 996 | 1251 |

## Writing & Preference

- Phi 3 Mini 128k Instruct: 27.1 (#301)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1050 | 1230 |
| LMArena Creative Writing | 1024 | 1174 |
| LMArena Multi-Turn | 989 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Phi 3 Mini 128k Instruct better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.7 on the Noometry Index.

### Is Phi 3 Mini 128k Instruct or Qwen2.5-Coder-32B better for coding?

Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.8 versus 22.6 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 128k Instruct and Qwen2.5-Coder-32B share?

14 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen2.5-Coder-32B has 31.