# phi-3-medium 14B vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-14b-vs-qwen3-8-max
- 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 0 categories and Qwen3.8 Max in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.8 Max leads 61.7 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 27.6% for phi-3-medium 14B and 92.7% for Qwen3.8 Max.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 56.0 |
| Rank | 306 | 21 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Proprietary |

## Coding

- phi-3-medium 14B: 36.3 (#198)
- Qwen3.8 Max: 52.3 (#30)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1671 |
| FrontierSWE | — | 15.8% |
| SciCode | — | 52.9% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1499 |
| BigCodeBench Complete | 48.7% | — |

## Agentic & Tool Use

- phi-3-medium 14B: —
- Qwen3.8 Max: 42.6 (#17)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- phi-3-medium 14B: —
- Qwen3.8 Max: 53.4 (#26)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| Epoch Capabilities Index | 121.18 | 156.69 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LMArena Hard Prompts | — | 1493 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |

## Math

- phi-3-medium 14B: 25.2 (#249)
- Qwen3.8 Max: 73.1 (#15)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| LMArena Math | — | 1498 |
| MATH Level 5 | 17.6% | — |

## Knowledge

- phi-3-medium 14B: 9.1 (#301)
- Qwen3.8 Max: 61.7 (#25)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 27.6% | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1504 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## Multimodal

- phi-3-medium 14B: —
- Qwen3.8 Max: 36.9 (#70)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- phi-3-medium 14B: —
- Qwen3.8 Max: 56.6 (#18)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1468 |
| LMArena Chinese | — | 1537 |
| LMArena French | — | 1502 |
| LMArena German | — | 1489 |
| LMArena Japanese | — | 1466 |
| LMArena Korean | — | 1467 |
| LMArena Russian | — | 1478 |
| LMArena Spanish | — | 1495 |

## Instruction Following

- phi-3-medium 14B: —
- Qwen3.8 Max: 77.7 (#19)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1478 |

## Long Context

- phi-3-medium 14B: —
- Qwen3.8 Max: 45.5 (#30)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1486 |

## Writing & Preference

- phi-3-medium 14B: —
- Qwen3.8 Max: 67.0 (#31)

| Benchmark | phi-3-medium 14B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1480 |
| LMArena Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1487 |

## FAQ

### Is phi-3-medium 14B better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 29.1 on the Noometry Index.

### Is phi-3-medium 14B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 36.3 in the Noometry coding category.

### How many benchmarks do phi-3-medium 14B and Qwen3.8 Max share?

2 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen3.8 Max has 38.