# phi-3-medium 14B vs Qwen Plus

> Qwen Plus is the stronger model overall, scoring 36.7 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-14b-vs-qwen-plus
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Qwen Plus in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Plus leads 27.4 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 17.6% for phi-3-medium 14B and 65.3% for Qwen Plus.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 36.7 |
| Rank | 306 | 204 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.20 |
| Weights | Open | Proprietary |

## Coding

- phi-3-medium 14B: 36.3 (#198)
- Qwen Plus: 38.3 (#163)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1328 |
| BigCodeBench Complete | 48.7% | — |

## Reasoning

- phi-3-medium 14B: —
- Qwen Plus: 27.6 (#101)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | — | 63.3% |
| LMArena Hard Prompts | — | 1317 |
| DTBench | — | 81.1% |
| LMCA | — | 24% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.18 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |

## Math

- phi-3-medium 14B: 25.2 (#249)
- Qwen Plus: 22.0 (#266)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| MATH Level 5 | 17.6% | 65.3% |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| LMArena Math | — | 1326 |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- phi-3-medium 14B: 9.1 (#301)
- Qwen Plus: 27.4 (#245)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 27.6% | 48.1% |
| LMArena Expert | — | 1328 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## Multilingual

- phi-3-medium 14B: —
- Qwen Plus: 45.3 (#170)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| LMArena Non-English | — | 1310 |
| LMArena Chinese | — | 1347 |
| LMArena Japanese | — | 1251 |
| LMArena Russian | — | 1323 |

## Instruction Following

- phi-3-medium 14B: —
- Qwen Plus: 69.0 (#176)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | — | 1303 |

## Long Context

- phi-3-medium 14B: —
- Qwen Plus: 40.3 (#153)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | — | 1325 |

## Writing & Preference

- phi-3-medium 14B: —
- Qwen Plus: 52.4 (#171)

| Benchmark | phi-3-medium 14B | Qwen Plus |
|---|---|---|
| LMArena Text | — | 1326 |
| LMArena Creative Writing | — | 1293 |
| LMArena Multi-Turn | — | 1336 |

## FAQ

### Is phi-3-medium 14B better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 36.7 to 29.1 on the Noometry Index.

### Is phi-3-medium 14B or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.3 versus 36.3 in the Noometry coding category.

### How many benchmarks do phi-3-medium 14B and Qwen Plus share?

2 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen Plus has 20.