Noometry

Model comparison

Phi-4 vs Qwen3.7 Plus

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 31.2 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.

Last verified . 21 shared benchmarks.

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

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 50.5 to 20.8.
  • 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.

Side by side

Phi-4Qwen3.7 Plus
ProviderMicrosoftAlibaba (Qwen)
Noometry Index31.245.3
Released2024-12-112026-06-02
WeightsOpenProprietary
Context window128K1M
Max output4K131K
Input $ / M tokens$0.07$0.40
Output $ / M tokens$0.14$1.60
Results tracked3732

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3.7 Plus leads

Phi-4: 34.4 (#239), Qwen3.7 Plus: 36.6 (#206)

BenchmarkPhi-4Qwen3.7 Plus
LMArena Coding12311473
FrontierCode—10.2%
SciCode—45.5%
BigCodeBench Instruct45.5%—
LiveBench Coding30.7%—
BigCodeBench Complete55.4%—

Agentic & Tool Use Phi-4 leads

Phi-4: 22.8 (#128), Qwen3.7 Plus: 21.4 (#138)

BenchmarkPhi-4Qwen3.7 Plus
Berkeley Function Calling Leaderboard28.8%—
OSWorld 2.0—2.8%
BALROG11.6%—

Reasoning Qwen3.7 Plus leads

Phi-4: 17.7 (#291), Qwen3.7 Plus: 39.3 (#59)

BenchmarkPhi-4Qwen3.7 Plus
Chess Puzzles1%24%
LMArena Hard Prompts12201460
Epoch Capabilities Index130.42147.37
NYT Connections (extended)—74.8%
CritPt—9.1%
LiveBench Reasoning47.8%—
Mystery Game Puzzles—17%
DTBench—84%
LiveBench Data Analysis45.2%—
LMCA—37.6%
LiveBench41.6%—

Math Qwen3.7 Plus leads

Phi-4: 20.8 (#285), Qwen3.7 Plus: 50.5 (#56)

BenchmarkPhi-4Qwen3.7 Plus
OTIS Mock AIME 2024-202513.8%93.3%
LMArena Math12461466
FrontierMath (Tiers 1-3)—34.4%
LiveBench Math42%—
MATH Level 564.9%—

Knowledge Qwen3.7 Plus leads

Phi-4: 32.6 (#209), Qwen3.7 Plus: 54.9 (#51)

BenchmarkPhi-4Qwen3.7 Plus
GPQA Diamond56.1%87.9%
LMArena Expert12031467
Confabulations29.4%—
Vectara Hallucination Rate3.7%—
MMLU84.8%—

Multimodal Not comparable

Phi-4: —, Qwen3.7 Plus: 41.8 (#33)

BenchmarkPhi-4Qwen3.7 Plus
LMArena Vision—1279
LMArena Document—1444

Multilingual Qwen3.7 Plus leads

Phi-4: 37.2 (#237), Qwen3.7 Plus: 54.8 (#38)

BenchmarkPhi-4Qwen3.7 Plus
LMArena Non-English11971445
LMArena Chinese12121510
LMArena French12241473
LMArena German12221471
LMArena Japanese11581413
LMArena Korean11511415
LMArena Russian12091457
LMArena Spanish12341457

Instruction Following Qwen3.7 Plus leads

Phi-4: 60.4 (#251), Qwen3.7 Plus: 75.8 (#52)

BenchmarkPhi-4Qwen3.7 Plus
LMArena Instruction Following12011440
LiveBench Instruction Following58.4%—

Long Context Qwen3.7 Plus leads

Phi-4: 36.9 (#226), Qwen3.7 Plus: 44.5 (#65)

BenchmarkPhi-4Qwen3.7 Plus
LMArena Longer Query12171455

Writing & Preference Qwen3.7 Plus leads

Phi-4: 40.5 (#244), Qwen3.7 Plus: 64.3 (#56)

BenchmarkPhi-4Qwen3.7 Plus
LMArena Text12171455
LMArena Creative Writing11821439
LMArena Multi-Turn12061460
Short-Story Creative Writing62.6%—
LiveBench Language25.6%—

Frequently asked questions

Is Phi-4 better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 31.2 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: 36.6 versus 34.4 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.

Related comparisons

Go deeper