Noometry

Model comparison

Qwen3.6 Max Preview vs Qwen3 Max

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 43.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Qwen3.6 Max Preview Alibaba (Qwen)

51.1

Rank #36 Confirmed

Qwen3 Max Alibaba (Qwen)

43.5

Rank #82 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Qwen3.6 Max Preview scores higher in 8 categories and Qwen3 Max in 0 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.6 Max Preview leads 40.8 to 22.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 74.1% for Qwen3.6 Max Preview and 30.1% for Qwen3 Max.
  • Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.

Side by side

Qwen3.6 Max PreviewQwen3 Max
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index51.143.5
Released2026-04-202025-09-23
WeightsProprietaryProprietary
Context window262K262K
Max output66K66K
Input $ / M tokens$1.30$1.20
Output $ / M tokens$7.80$6
Results tracked2933

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

Category by category

Coding Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 48.6 (#50), Qwen3 Max: 42.4 (#93)

BenchmarkQwen3.6 Max PreviewQwen3 Max
LMArena Coding14721456
SWE-bench Verified76.7%—
LMArena WebDev1482—
ALE-Bench—370.45

Agentic & Tool Use Not comparable

Qwen3.6 Max Preview: —, Qwen3 Max: —

BenchmarkQwen3.6 Max PreviewQwen3 Max
Vending-Bench 24,25471.56

Reasoning Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 40.8 (#47), Qwen3 Max: 22.0 (#186)

BenchmarkQwen3.6 Max PreviewQwen3 Max
NYT Connections (extended)74.1%30.1%
Chess Puzzles20%4%
LMArena Hard Prompts14571448
Mystery Game Puzzles19%5%
DTBench87.2%82.1%
LMCA42.5%28.3%
Epoch Capabilities Index149.27142.41
SimpleBench63%—
Kagi LLM Benchmark—72.5%

Math Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 52.2 (#40), Qwen3 Max: 37.6 (#94)

BenchmarkQwen3.6 Max PreviewQwen3 Max
OTIS Mock AIME 2024-202591.1%73.3%
LMArena Math14651447
FrontierMath (Tiers 1-3)—18.9%
MATH Level 5—97.1%
FrontierMath (Feb 2025 set)23.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 57.6 (#35), Qwen3 Max: 48.1 (#72)

BenchmarkQwen3.6 Max PreviewQwen3 Max
GPQA Diamond87.4%72.6%
SimpleQA Verified52%48.7%
LMArena Expert14761457

Multilingual Too close to call

Qwen3.6 Max Preview: 54.3 (#46), Qwen3 Max: 53.9 (#58)

BenchmarkQwen3.6 Max PreviewQwen3 Max
LMArena Non-English14361429
LMArena Chinese14871479
LMArena French14491450
LMArena Russian14441428
LMArena Spanish14521463
LMArena German—1463
LMArena Japanese—1399
LMArena Korean—1397

Instruction Following Too close to call

Qwen3.6 Max Preview: 75.8 (#51), Qwen3 Max: 75.0 (#81)

BenchmarkQwen3.6 Max PreviewQwen3 Max
LMArena Instruction Following14371420

Long Context Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 44.6 (#59), Qwen3 Max: 41.6 (#129)

BenchmarkQwen3.6 Max PreviewQwen3 Max
LMArena Longer Query14571439
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Qwen3.6 Max Preview leads

Qwen3.6 Max Preview: 64.0 (#58), Qwen3 Max: 62.6 (#72)

BenchmarkQwen3.6 Max PreviewQwen3 Max
LMArena Text14471439
LMArena Creative Writing14351401
LMArena Multi-Turn14561446

Frequently asked questions

Is Qwen3.6 Max Preview better than Qwen3 Max?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 43.5 on the Noometry Index.

Which is cheaper, Qwen3.6 Max Preview or Qwen3 Max?

Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.

Is Qwen3.6 Max Preview or Qwen3 Max better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Qwen3.6 Max Preview and Qwen3 Max share?

24 benchmarks have published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper