# Phi 3 Mini 128k Instruct vs Qwen3.5 27B

> Qwen3.5 27B is the stronger model overall, scoring 41.4 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-128k-instruct-vs-qwen3-5-27b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen3.5 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 27B leads 59.5 to 27.3.

## Snapshot

| | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 41.4 |
| Rank | 303 | 127 |
| Context | — | 262K |
| Input $/M | — | $0.30 |
| Output $/M | — | $2.40 |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 128k Instruct: 28.3 (#307)
- Qwen3.5 27B: 38.6 (#159)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Coding | 1040 | 1427 |
| LMArena WebDev | — | 1357 |
| WeirdML | — | 39.5% |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 349.45 |

## Agentic & Tool Use

- Phi 3 Mini 128k Instruct: —
- Qwen3.5 27B: —

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |

## Reasoning

- Phi 3 Mini 128k Instruct: 18.7 (#254)
- Qwen3.5 27B: 26.6 (#116)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1414 |
| NYT Connections (extended) | — | 47.9% |
| Thematic Generalization | — | 45.5% |
| DTBench | — | 82.4% |
| LMCA | — | 34% |

## Math

- Phi 3 Mini 128k Instruct: 29.2 (#220)
- Qwen3.5 27B: 36.8 (#103)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1089 | 1428 |
| MathArena Final-Answer Competitions | — | 56.7% |

## Knowledge

- Phi 3 Mini 128k Instruct: 26.3 (#251)
- Qwen3.5 27B: 37.4 (#149)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 984 | 1428 |
| Vectara Hallucination Rate | — | 12.1% |

## Multimodal

- Phi 3 Mini 128k Instruct: —
- Qwen3.5 27B: 38.7 (#56)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1240 |

## Multilingual

- Phi 3 Mini 128k Instruct: 25.4 (#280)
- Qwen3.5 27B: 51.0 (#112)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1000 | 1390 |
| LMArena Chinese | 1016 | 1478 |
| LMArena French | 1038 | 1409 |
| LMArena German | 1006 | 1393 |
| LMArena Japanese | 899 | 1345 |
| LMArena Korean | 856 | 1359 |
| LMArena Russian | 1004 | 1389 |
| LMArena Spanish | 1058 | 1408 |

## Instruction Following

- Phi 3 Mini 128k Instruct: 52.1 (#289)
- Qwen3.5 27B: 73.7 (#114)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1393 |

## Long Context

- Phi 3 Mini 128k Instruct: 30.3 (#284)
- Qwen3.5 27B: 43.1 (#103)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 996 | 1413 |

## Writing & Preference

- Phi 3 Mini 128k Instruct: 27.3 (#296)
- Qwen3.5 27B: 59.5 (#106)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1050 | 1409 |
| LMArena Creative Writing | 1024 | 1362 |
| LMArena Multi-Turn | 989 | 1410 |

## FAQ

### Is Phi 3 Mini 128k Instruct better than Qwen3.5 27B?

Qwen3.5 27B is the stronger model overall, scoring 41.4 to 29.1 on the Noometry Index.

### Is Phi 3 Mini 128k Instruct or Qwen3.5 27B better for coding?

Qwen3.5 27B scores higher on coding benchmarks: 38.6 versus 28.3 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3.5 27B share?

17 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3.5 27B has 28.