# Phi 3 Small 8k Instruct vs Qwen3 32B

> Qwen3 32B is the stronger model overall, scoring 39.2 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-small-8k-instruct-vs-qwen3-32b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 0 categories and Qwen3 32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 31.1.

## Snapshot

| | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.3 | 39.2 |
| Rank | 314 | 172 |
| Context | — | 131K |
| Input $/M | — | $0.70 |
| Output $/M | — | $2.80 |
| Weights | Open | Open |

## Coding

- Phi 3 Small 8k Instruct: 27.9 (#318)
- Qwen3 32B: 37.7 (#190)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1101 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| LiveBench Coding | 20.3% | — |

## Agentic & Tool Use

- Phi 3 Small 8k Instruct: —
- Qwen3 32B: 32.6 (#62)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Phi 3 Small 8k Instruct: 14.8 (#323)
- Qwen3 32B: 20.2 (#241)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1334 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | 15.9% | — |
| DTBench | — | 67.5% |
| LiveBench Data Analysis | 30.3% | — |
| LMCA | — | 17.3% |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| Epoch Capabilities Index | — | 138.51 |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |

## Math

- Phi 3 Small 8k Instruct: 27.6 (#248)
- Qwen3 32B: 39.7 (#99)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Math | 1151 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LiveBench Math | 17.6% | — |

## Knowledge

- Phi 3 Small 8k Instruct: 29.1 (#240)
- Qwen3 32B: 40.0 (#125)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Expert | 1067 | 1362 |
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |

## Multilingual

- Phi 3 Small 8k Instruct: 28.5 (#272)
- Qwen3 32B: 45.6 (#167)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1058 | 1317 |
| LMArena Chinese | 1061 | 1357 |
| LMArena German | 1080 | 1341 |
| LMArena Russian | 1111 | 1311 |
| LMArena French | 1135 | — |
| LMArena Japanese | 966 | — |
| LMArena Korean | 894 | — |
| LMArena Spanish | 1111 | — |

## Instruction Following

- Phi 3 Small 8k Instruct: 51.9 (#292)
- Qwen3 32B: 68.9 (#179)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1087 | 1305 |
| LiveBench Instruction Following | 47.2% | — |

## Long Context

- Phi 3 Small 8k Instruct: 33.0 (#267)
- Qwen3 32B: 43.8 (#87)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1088 | 1327 |
| Fiction.LiveBench | — | 74.2% |

## Writing & Preference

- Phi 3 Small 8k Instruct: 31.1 (#284)
- Qwen3 32B: 52.9 (#163)

| Benchmark | Phi 3 Small 8k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | 1110 | 1340 |
| LMArena Creative Writing | 1083 | 1297 |
| LMArena Multi-Turn | 1068 | 1331 |
| LiveBench Language | 12.9% | — |

## FAQ

### Is Phi 3 Small 8k Instruct better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 39.2 to 29.3 on the Noometry Index.

### Is Phi 3 Small 8k Instruct or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 27.9 in the Noometry coding category.

### How many benchmarks do Phi 3 Small 8k Instruct and Qwen3 32B share?

13 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen3 32B has 26.