# Phi 3 Medium 4k Instruct vs Qwen3.6 Max Preview

> Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-4k-instruct-vs-qwen3-6-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Phi 3 Medium 4k Instruct scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.6 Max Preview leads 64.0 to 34.3.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 32.4 | 51.1 |
| Rank | 246 | 36 |
| Context | — | 262K |
| Input $/M | — | $1.30 |
| Output $/M | — | $7.80 |
| Weights | Open | Proprietary |

## Coding

- Phi 3 Medium 4k Instruct: 32.3 (#263)
- Qwen3.6 Max Preview: 48.6 (#50)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1130 | 1472 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |

## Agentic & Tool Use

- Phi 3 Medium 4k Instruct: —
- Qwen3.6 Max Preview: —

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |

## Reasoning

- Phi 3 Medium 4k Instruct: 20.8 (#214)
- Qwen3.6 Max Preview: 40.8 (#47)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1457 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.27 |

## Math

- Phi 3 Medium 4k Instruct: 30.9 (#202)
- Qwen3.6 Max Preview: 52.2 (#40)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1173 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Phi 3 Medium 4k Instruct: 29.6 (#226)
- Qwen3.6 Max Preview: 57.6 (#35)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1108 | 1476 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |

## Multilingual

- Phi 3 Medium 4k Instruct: 30.8 (#258)
- Qwen3.6 Max Preview: 54.3 (#46)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1094 | 1436 |
| LMArena Chinese | 1108 | 1487 |
| LMArena French | 1109 | 1449 |
| LMArena Russian | 1145 | 1444 |
| LMArena Spanish | 1095 | 1452 |
| LMArena German | 1101 | — |
| LMArena Japanese | 1042 | — |
| LMArena Korean | 954 | — |

## Instruction Following

- Phi 3 Medium 4k Instruct: 57.8 (#263)
- Qwen3.6 Max Preview: 75.8 (#51)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1114 | 1437 |

## Long Context

- Phi 3 Medium 4k Instruct: 33.9 (#250)
- Qwen3.6 Max Preview: 44.6 (#59)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1120 | 1457 |

## Writing & Preference

- Phi 3 Medium 4k Instruct: 34.3 (#267)
- Qwen3.6 Max Preview: 64.0 (#58)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1138 | 1447 |
| LMArena Creative Writing | 1106 | 1435 |
| LMArena Multi-Turn | 1088 | 1456 |

## FAQ

### Is Phi 3 Medium 4k Instruct better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 32.4 on the Noometry Index.

### Is Phi 3 Medium 4k Instruct or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 32.3 in the Noometry coding category.

### How many benchmarks do Phi 3 Medium 4k Instruct and Qwen3.6 Max Preview share?

14 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Qwen3.6 Max Preview has 29.