# Phi-3.5-mini vs Qwen3 32B

> Qwen3 32B has enough public results to be ranked (#172); Phi-3.5-mini does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/phi-3-5-mini-vs-qwen3-32b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Qwen3 32B leads 37.7 to 34.6.

## Snapshot

| | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 36.9 | 39.2 |
| Rank | — | 172 |
| Context | — | 131K |
| Input $/M | — | $0.70 |
| Output $/M | — | $2.80 |
| Weights | Open | Open |

## Coding

- Phi-3.5-mini: 34.6 (#232)
- Qwen3 32B: 37.7 (#190)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 32.8% | — |
| LMArena Coding | — | 1358 |
| BigCodeBench Complete | 38.5% | — |

## Agentic & Tool Use

- Phi-3.5-mini: —
- Qwen3 32B: 32.6 (#62)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Phi-3.5-mini: —
- Qwen3 32B: 20.2 (#241)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | — | 1334 |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
| PIQA | 81% | — |

## Math

- Phi-3.5-mini: —
- Qwen3 32B: 39.7 (#99)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |
| GSM8K | 86.2% | — |

## Knowledge

- Phi-3.5-mini: —
- Qwen3 32B: 40.0 (#125)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
| BoolQ | 78% | — |

## Multilingual

- Phi-3.5-mini: —
- Qwen3 32B: 45.6 (#167)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |

## Instruction Following

- Phi-3.5-mini: —
- Qwen3 32B: 68.9 (#179)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |

## Long Context

- Phi-3.5-mini: —
- Qwen3 32B: 43.8 (#87)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |

## Writing & Preference

- Phi-3.5-mini: —
- Qwen3 32B: 52.9 (#163)

| Benchmark | Phi-3.5-mini | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |

## FAQ

### Is Phi-3.5-mini better than Qwen3 32B?

Qwen3 32B has enough public results to be ranked (#172); Phi-3.5-mini does not yet, so treat this comparison as directional.

### Is Phi-3.5-mini or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 34.6 in the Noometry coding category.

### How many benchmarks do Phi-3.5-mini and Qwen3 32B share?

0 benchmarks have published results for both models. Phi-3.5-mini has 5 scored results on Noometry and Qwen3 32B has 26.