# Phi 3 Mini 128k Instruct vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-128k-instruct-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Plus leads 64.5 to 27.3.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 45.0 |
| Rank | 303 | 66 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Phi 3 Mini 128k Instruct: 28.3 (#307)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1040 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |

## Agentic & Tool Use

- Phi 3 Mini 128k Instruct: —
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Phi 3 Mini 128k Instruct: 18.7 (#254)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1460 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.39 |

## Math

- Phi 3 Mini 128k Instruct: 29.2 (#220)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1089 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |

## Knowledge

- Phi 3 Mini 128k Instruct: 26.3 (#251)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 984 | 1467 |
| GPQA Diamond | — | 87.9% |

## Multimodal

- Phi 3 Mini 128k Instruct: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- Phi 3 Mini 128k Instruct: 25.4 (#280)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1000 | 1445 |
| LMArena Chinese | 1016 | 1510 |
| LMArena French | 1038 | 1471 |
| LMArena German | 1006 | 1471 |
| LMArena Japanese | 899 | 1411 |
| LMArena Korean | 856 | 1416 |
| LMArena Russian | 1004 | 1457 |
| LMArena Spanish | 1058 | 1453 |

## Instruction Following

- Phi 3 Mini 128k Instruct: 52.1 (#289)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1023 | 1439 |

## Long Context

- Phi 3 Mini 128k Instruct: 30.3 (#284)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 996 | 1454 |

## Writing & Preference

- Phi 3 Mini 128k Instruct: 27.3 (#296)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1050 | 1454 |
| LMArena Creative Writing | 1024 | 1439 |
| LMArena Multi-Turn | 989 | 1459 |

## FAQ

### Is Phi 3 Mini 128k Instruct better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 29.1 on the Noometry Index.

### Is Phi 3 Mini 128k Instruct or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 28.3 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3.7 Plus share?

17 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3.7 Plus has 32.