# phi-3-medium 14B vs Qwen2.5 32B Instruct

> phi-3-medium 14B and Qwen2.5 32B Instruct score almost the same on the Noometry Index (29.1 vs 29.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/phi-3-medium-14b-vs-qwen2-5-32b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Qwen2.5 32B Instruct in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 32B Instruct leads 24.9 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 17.6% for phi-3-medium 14B and 56.1% for Qwen2.5 32B Instruct.

## Snapshot

| | phi-3-medium 14B | Qwen2.5 32B Instruct |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 29.7 |
| Rank | 306 | 291 |
| Context | — | 131K |
| Input $/M | — | $0.70 |
| Output $/M | — | $2.80 |
| Weights | Open | Open |

## Coding

- phi-3-medium 14B: 36.3 (#198)
- Qwen2.5 32B Instruct: 38.1 (#165)

| Benchmark | phi-3-medium 14B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 45% |
| BigCodeBench Complete | 48.7% | 52.3% |

## Reasoning

- phi-3-medium 14B: —
- Qwen2.5 32B Instruct: 18.5 (#262)

| Benchmark | phi-3-medium 14B | Qwen2.5 32B Instruct |
|---|---|---|
| Epoch Capabilities Index | 121.18 | 128.52 |
| Chess Puzzles | — | 0% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |

## Math

- phi-3-medium 14B: 25.2 (#249)
- Qwen2.5 32B Instruct: 15.3 (#289)

| Benchmark | phi-3-medium 14B | Qwen2.5 32B Instruct |
|---|---|---|
| MATH Level 5 | 17.6% | 56.1% |
| OTIS Mock AIME 2024-2025 | — | 7.4% |

## Knowledge

- phi-3-medium 14B: 9.1 (#301)
- Qwen2.5 32B Instruct: 24.9 (#259)

| Benchmark | phi-3-medium 14B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 27.6% | 46.1% |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## FAQ

### Is phi-3-medium 14B better than Qwen2.5 32B Instruct?

phi-3-medium 14B and Qwen2.5 32B Instruct score almost the same on the Noometry Index (29.1 vs 29.7), so choose on price, context window or the category you care about most.

### Is phi-3-medium 14B or Qwen2.5 32B Instruct better for coding?

Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.1 versus 36.3 in the Noometry coding category.

### How many benchmarks do phi-3-medium 14B and Qwen2.5 32B Instruct share?

5 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen2.5 32B Instruct has 7.