Noometry

Model comparison

Phi-4 vs Qwen3.7 Max

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 30.9 on the Noometry Index. Phi-4 costs 43× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

Phi-4 Microsoft

30.9

Rank #269 Confirmed

Qwen3.7 Max Alibaba (Qwen)

51.4

Rank #35 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Phi-4 scores higher in 1 category and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.7 Max leads 62.3 to 19.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 13.8% for Phi-4 and 95.6% for Qwen3.7 Max.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
  • Qwen3.7 Max accepts more context: 1M tokens versus 128K.
  • Phi-4 has downloadable open weights; the other is API-only.

Side by side

Phi-4Qwen3.7 Max
ProviderMicrosoftAlibaba (Qwen)
Noometry Index30.951.4
Released2024-12-112026-05-19
WeightsOpenProprietary
Context window128K1M
Max output4K131K
Input $ / M tokens$0.07$2.50
Output $ / M tokens$0.14$7.50
Results tracked3733

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

Category by category

Coding Qwen3.7 Max leads

Phi-4: 33.8 (#237), Qwen3.7 Max: 50.2 (#43)

BenchmarkPhi-4Qwen3.7 Max
LMArena Coding12311498
SWE-bench Verified—77.3%
LMArena WebDev—1515
SciCode—48.8%
BigCodeBench Instruct45.5%—
LiveBench Coding30.7%—
BigCodeBench Complete55.4%—
ALE-Bench—1,189

Agentic & Tool Use Too close to call

Phi-4: 22.6 (#120), Qwen3.7 Max: 21.8 (#129)

BenchmarkPhi-4Qwen3.7 Max
Berkeley Function Calling Leaderboard28.8%—
BALROG11.6%—
GBAEval—0.4%

Reasoning Qwen3.7 Max leads

Phi-4: 17.0 (#287), Qwen3.7 Max: 48.4 (#36)

BenchmarkPhi-4Qwen3.7 Max
Chess Puzzles1%19%
LMArena Hard Prompts12201483
Epoch Capabilities Index130.43153.74
SimpleBench—70.4%
NYT Connections (extended)—85.1%
CritPt—13.4%
EBR-Bench—9.5%
LiveBench Reasoning47.8%—
Mystery Game Puzzles—32%
DTBench—92.3%
LiveBench Data Analysis45.2%—
LMCA—44%
LiveBench41.6%—

Math Qwen3.7 Max leads

Phi-4: 19.6 (#279), Qwen3.7 Max: 62.3 (#26)

BenchmarkPhi-4Qwen3.7 Max
OTIS Mock AIME 2024-202513.8%95.6%
LMArena Math12461488
FrontierMath (Tiers 1-3)—64.6%
FrontierMath Tier 4—34.1%
ProofBench—26%
LiveBench Math42%—
MATH Level 564.9%—

Knowledge Qwen3.7 Max leads

Phi-4: 32.5 (#204), Qwen3.7 Max: 61.7 (#24)

BenchmarkPhi-4Qwen3.7 Max
GPQA Diamond56.1%90.9%
LMArena Expert12031488
SimpleQA Verified—55.8%
Confabulations29.4%—
Vectara Hallucination Rate3.7%—
MMLU84.8%—

Multilingual Qwen3.7 Max leads

Phi-4: 37.4 (#232), Qwen3.7 Max: 57.1 (#13)

BenchmarkPhi-4Qwen3.7 Max
LMArena Non-English11971475
LMArena Chinese12111533
LMArena Russian12091482
LMArena French1223—
LMArena German1222—
LMArena Japanese1158—
LMArena Korean1151—
LMArena Spanish1234—

Instruction Following Qwen3.7 Max leads

Phi-4: 60.6 (#246), Qwen3.7 Max: 76.9 (#34)

BenchmarkPhi-4Qwen3.7 Max
LMArena Instruction Following12011460
LiveBench Instruction Following58.4%—

Long Context Qwen3.7 Max leads

Phi-4: 36.9 (#221), Qwen3.7 Max: 45.4 (#34)

BenchmarkPhi-4Qwen3.7 Max
LMArena Longer Query12171484

Writing & Preference Qwen3.7 Max leads

Phi-4: 40.7 (#239), Qwen3.7 Max: 65.2 (#52)

BenchmarkPhi-4Qwen3.7 Max
LMArena Text12171476
LMArena Creative Writing11821450
LMArena Multi-Turn12061482
Short-Story Creative Writing62.6%—
EQ-Bench 4—1110
LiveBench Language25.6%—

Frequently asked questions

Is Phi-4 better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 30.9 on the Noometry Index. Phi-4 costs 43× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

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

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

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

Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

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

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

16 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3.7 Max has 33.

Related comparisons

Go deeper