Noometry

Model comparison

Qwen3.7 Plus vs Qwen3 Max

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 43.7 on the Noometry Index.

Last verified . 26 shared benchmarks.

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Qwen3.7 Plus scores higher in 7 categories and Qwen3 Max in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.7 Plus leads 39.3 to 22.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 74.8% for Qwen3.7 Plus and 30.1% for Qwen3 Max.
  • Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • Qwen3.7 Plus accepts more context: 1M tokens versus 262K.

Side by side

Qwen3.7 PlusQwen3 Max
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index45.343.7
Released2026-06-022025-09-23
WeightsProprietaryProprietary
Context window1M262K
Max output131K66K
Input $ / M tokens$0.40$1.20
Output $ / M tokens$1.60$6
Results tracked3233

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

Category by category

Coding Qwen3 Max leads

Qwen3.7 Plus: 36.6 (#206), Qwen3 Max: 43.0 (#93)

BenchmarkQwen3.7 PlusQwen3 Max
LMArena Coding14731456
FrontierCode10.2%—
SciCode45.5%—
ALE-Bench—370.45

Agentic & Tool Use Not comparable

Qwen3.7 Plus: 21.4 (#138), Qwen3 Max: —

BenchmarkQwen3.7 PlusQwen3 Max
OSWorld 2.02.8%—
Vending-Bench 2—71.56

Reasoning Qwen3.7 Plus leads

Qwen3.7 Plus: 39.3 (#59), Qwen3 Max: 22.6 (#190)

BenchmarkQwen3.7 PlusQwen3 Max
NYT Connections (extended)74.8%30.1%
Chess Puzzles24%4%
LMArena Hard Prompts14601448
Mystery Game Puzzles17%5%
DTBench84%82.1%
LMCA37.6%28.3%
Epoch Capabilities Index147.37142.38
Kagi LLM Benchmark—72.5%
CritPt9.1%—

Math Qwen3.7 Plus leads

Qwen3.7 Plus: 50.5 (#56), Qwen3 Max: 38.7 (#131)

BenchmarkQwen3.7 PlusQwen3 Max
FrontierMath (Tiers 1-3)34.4%18.9%
OTIS Mock AIME 2024-202593.3%73.3%
LMArena Math14661446
MATH Level 5—97.1%

Knowledge Qwen3.7 Plus leads

Qwen3.7 Plus: 54.9 (#51), Qwen3 Max: 48.1 (#78)

BenchmarkQwen3.7 PlusQwen3 Max
GPQA Diamond87.9%72.6%
LMArena Expert14671455
SimpleQA Verified—48.7%

Multimodal Not comparable

Qwen3.7 Plus: 41.8 (#33), Qwen3 Max: —

BenchmarkQwen3.7 PlusQwen3 Max
LMArena Vision1279—
LMArena Document1444—

Multilingual Qwen3.7 Plus leads

Qwen3.7 Plus: 54.8 (#38), Qwen3 Max: 53.7 (#62)

BenchmarkQwen3.7 PlusQwen3 Max
LMArena Non-English14451429
LMArena Chinese15101478
LMArena French14731449
LMArena German14711463
LMArena Japanese14131397
LMArena Korean14151399
LMArena Russian14571428
LMArena Spanish14571462

Instruction Following Too close to call

Qwen3.7 Plus: 75.8 (#52), Qwen3 Max: 74.8 (#87)

BenchmarkQwen3.7 PlusQwen3 Max
LMArena Instruction Following14401419

Long Context Qwen3.7 Plus leads

Qwen3.7 Plus: 44.5 (#65), Qwen3 Max: 41.6 (#134)

BenchmarkQwen3.7 PlusQwen3 Max
LMArena Longer Query14551438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Qwen3.7 Plus leads

Qwen3.7 Plus: 64.3 (#56), Qwen3 Max: 62.4 (#76)

BenchmarkQwen3.7 PlusQwen3 Max
LMArena Text14551439
LMArena Creative Writing14391402
LMArena Multi-Turn14601446

Frequently asked questions

Is Qwen3.7 Plus better than Qwen3 Max?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 43.7 on the Noometry Index.

Which is cheaper, Qwen3.7 Plus or Qwen3 Max?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is Qwen3.7 Plus or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 36.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 262K.

How many benchmarks do Qwen3.7 Plus and Qwen3 Max share?

26 benchmarks have published results for both models. Qwen3.7 Plus has 32 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper