# Phi-4 vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 30.9 on the Noometry Index. Phi-4 costs 8.0× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/phi-4-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Phi-4 scores higher in 1 category and Qwen3.7 Plus in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 49.3 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 13.8% for Phi-4 and 93.3% for Qwen3.7 Plus.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.

## Snapshot

| | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 45.0 |
| Rank | 269 | 66 |
| Context | 128K | 1M |
| Input $/M | $0.07 | $0.40 |
| Output $/M | $0.14 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Phi-4: 33.8 (#237)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1231 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| BigCodeBench Complete | 55.4% | — |

## Agentic & Tool Use

- Phi-4: 22.6 (#120)
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| OSWorld 2.0 | — | 2.8% |
| BALROG | 11.6% | — |

## Reasoning

- Phi-4: 17.0 (#287)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 1% | 24% |
| LMArena Hard Prompts | 1220 | 1460 |
| Epoch Capabilities Index | 130.43 | 147.39 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| LiveBench Reasoning | 47.8% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LiveBench Data Analysis | 45.2% | — |
| LMCA | — | 37.6% |
| LiveBench | 41.6% | — |

## Math

- Phi-4: 19.6 (#279)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 13.8% | 93.3% |
| LMArena Math | 1246 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| LiveBench Math | 42% | — |
| MATH Level 5 | 64.9% | — |

## Knowledge

- Phi-4: 32.5 (#204)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 56.1% | 87.9% |
| LMArena Expert | 1203 | 1467 |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| MMLU | 84.8% | — |

## Multimodal

- Phi-4: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- Phi-4: 37.4 (#232)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1197 | 1445 |
| LMArena Chinese | 1211 | 1510 |
| LMArena French | 1223 | 1471 |
| LMArena German | 1222 | 1471 |
| LMArena Japanese | 1158 | 1411 |
| LMArena Korean | 1151 | 1416 |
| LMArena Russian | 1209 | 1457 |
| LMArena Spanish | 1234 | 1453 |

## Instruction Following

- Phi-4: 60.6 (#246)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1201 | 1439 |
| LiveBench Instruction Following | 58.4% | — |

## Long Context

- Phi-4: 36.9 (#221)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1217 | 1454 |

## Writing & Preference

- Phi-4: 40.7 (#239)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Phi-4 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1217 | 1454 |
| LMArena Creative Writing | 1182 | 1439 |
| LMArena Multi-Turn | 1206 | 1459 |
| Short-Story Creative Writing | 62.6% | — |
| LiveBench Language | 25.6% | — |

## FAQ

### Is Phi-4 better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 30.9 on the Noometry Index. Phi-4 costs 8.0× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.

### Which is cheaper, Phi-4 or Qwen3.7 Plus?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

### Is Phi-4 or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 128K.

### How many benchmarks do Phi-4 and Qwen3.7 Plus share?

21 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3.7 Plus has 32.