Noometry

Model comparison

Qwen2.5-Max vs Qwen3.6 Max Preview

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 40.1 on the Noometry Index.

Last verified . 15 shared benchmarks.

Qwen2.5-Max Alibaba (Qwen)

40.1

Rank #142 Confirmed

Qwen3.6 Max Preview Alibaba (Qwen)

51.1

Rank #36 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Qwen2.5-Max scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 to 34.8.

Side by side

Qwen2.5-MaxQwen3.6 Max Preview
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index40.151.1
Released2025-01-252026-04-20
WeightsProprietaryProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.30
Output $ / M tokens—$7.80
Results tracked2729

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

Category by category

Coding Qwen3.6 Max Preview leads

Qwen2.5-Max: 41.2 (#118), Qwen3.6 Max Preview: 48.6 (#50)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Coding13591472
SWE-bench Verified—76.7%
LMArena WebDev—1482
LiveBench Coding64.4%—

Agentic & Tool Use Not comparable

Qwen2.5-Max: —, Qwen3.6 Max Preview: —

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
Vending-Bench 2—4,254

Reasoning Qwen3.6 Max Preview leads

Qwen2.5-Max: 24.6 (#144), Qwen3.6 Max Preview: 40.8 (#47)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Hard Prompts13601457
Epoch Capabilities Index132.54149.27
SimpleBench—63%
NYT Connections (extended)—74.1%
Chess Puzzles—20%
LiveBench Reasoning51.4%—
Mystery Game Puzzles—19%
DTBench—87.2%
LiveBench Data Analysis67.9%—
LMCA—42.5%
LiveBench62.3%—

Math Qwen3.6 Max Preview leads

Qwen2.5-Max: 34.3 (#162), Qwen3.6 Max Preview: 52.2 (#40)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Math13691465
OTIS Mock AIME 2024-2025—91.1%
LiveBench Math58.4%—
FrontierMath (Feb 2025 set)—23.1%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Qwen3.6 Max Preview leads

Qwen2.5-Max: 34.8 (#181), Qwen3.6 Max Preview: 57.6 (#35)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Expert13371476
GPQA Diamond—87.4%
SimpleQA Verified—52%
Confabulations21.8%—

Multilingual Qwen3.6 Max Preview leads

Qwen2.5-Max: 48.3 (#140), Qwen3.6 Max Preview: 54.3 (#46)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Non-English13521436
LMArena Chinese13821487
LMArena French13961449
LMArena Russian13531444
LMArena Spanish13771452
LMArena German1350—
LMArena Japanese1299—
LMArena Korean1304—

Instruction Following Qwen3.6 Max Preview leads

Qwen2.5-Max: 71.5 (#147), Qwen3.6 Max Preview: 75.8 (#51)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Instruction Following13351437
LiveBench Instruction Following75.3%—

Long Context Qwen3.6 Max Preview leads

Qwen2.5-Max: 41.3 (#137), Qwen3.6 Max Preview: 44.6 (#59)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Longer Query13581457

Writing & Preference Qwen3.6 Max Preview leads

Qwen2.5-Max: 55.6 (#141), Qwen3.6 Max Preview: 64.0 (#58)

BenchmarkQwen2.5-MaxQwen3.6 Max Preview
LMArena Text13671447
LMArena Creative Writing13391435
LMArena Multi-Turn13641456
Short-Story Creative Writing72.9%—
LiveBench Language56.3%—

Frequently asked questions

Is Qwen2.5-Max better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 40.1 on the Noometry Index.

Is Qwen2.5-Max or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 41.2 in the Noometry coding category.

How many benchmarks do Qwen2.5-Max and Qwen3.6 Max Preview share?

15 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3.6 Max Preview has 29.

Related comparisons

Go deeper