# phi-3-medium 14B vs Qwen3.5-Flash

> Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-14b-vs-qwen3-5-flash
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Qwen3.5-Flash in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 27.6% for phi-3-medium 14B and 82.3% for Qwen3.5-Flash.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 42.5 |
| Rank | 306 | 112 |
| Context | — | 1M |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.40 |
| Weights | Open | Proprietary |

## Coding

- phi-3-medium 14B: 36.8 (#201)
- Qwen3.5-Flash: 34.2 (#242)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | — | 1244 |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1412 |
| BigCodeBench Complete | 48.7% | — |
| ALE-Bench | — | 221.8 |

## Agentic & Tool Use

- phi-3-medium 14B: —
- Qwen3.5-Flash: —

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |

## Reasoning

- phi-3-medium 14B: —
- Qwen3.5-Flash: 33.7 (#72)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| Epoch Capabilities Index | 121.23 | 143.98 |
| Chess Puzzles | — | 21% |
| LMArena Hard Prompts | — | 1403 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |

## Math

- phi-3-medium 14B: 27.3 (#250)
- Qwen3.5-Flash: 37.4 (#158)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 18.2% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| LMArena Math | — | 1407 |
| MATH Level 5 | 17.6% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- phi-3-medium 14B: 9.1 (#306)
- Qwen3.5-Flash: 43.2 (#93)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 27.6% | 82.3% |
| SimpleQA Verified | — | 20.3% |
| Vectara Hallucination Rate | — | 10.5% |
| LMArena Expert | — | 1407 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## Multilingual

- phi-3-medium 14B: —
- Qwen3.5-Flash: 50.5 (#121)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1412 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1368 |
| LMArena Korean | — | 1344 |
| LMArena Russian | — | 1379 |
| LMArena Spanish | — | 1400 |

## Instruction Following

- phi-3-medium 14B: —
- Qwen3.5-Flash: 72.6 (#139)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | — | 1374 |

## Long Context

- phi-3-medium 14B: —
- Qwen3.5-Flash: 42.4 (#124)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | — | 1392 |

## Writing & Preference

- phi-3-medium 14B: —
- Qwen3.5-Flash: 57.9 (#122)

| Benchmark | phi-3-medium 14B | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | — | 1397 |
| LMArena Creative Writing | — | 1343 |
| LMArena Multi-Turn | — | 1393 |

## FAQ

### Is phi-3-medium 14B better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 29.7 on the Noometry Index.

### Is phi-3-medium 14B or Qwen3.5-Flash better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.2 in the Noometry coding category.

### How many benchmarks do phi-3-medium 14B and Qwen3.5-Flash share?

2 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen3.5-Flash has 32.