Noometry

Model comparison

Qwen3.5 Max Preview vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 45.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Qwen3.5 Max Preview Alibaba (Qwen)

45.3

Rank #71 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Qwen3.5 Max Preview scores higher in 0 categories and Qwen3.8 Max in 8 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 40.1.

Side by side

Qwen3.5 Max PreviewQwen3.8 Max
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index45.356.8
Released—2026-08-02
WeightsProprietaryProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1739

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

Category by category

Coding Qwen3.8 Max leads

Qwen3.5 Max Preview: 44.0 (#77), Qwen3.8 Max: 53.5 (#29)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Coding14871502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%

Agentic & Tool Use Not comparable

Qwen3.5 Max Preview: —, Qwen3.8 Max: 45.4 (#14)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Qwen3.8 Max leads

Qwen3.5 Max Preview: 30.8 (#84), Qwen3.8 Max: 54.4 (#26)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Hard Prompts14831496
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%
Epoch Capabilities Index—156.41

Math Qwen3.8 Max leads

Qwen3.5 Max Preview: 40.1 (#94), Qwen3.8 Max: 73.2 (#20)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Math14741499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—58%

Knowledge Qwen3.8 Max leads

Qwen3.5 Max Preview: 41.8 (#107), Qwen3.8 Max: 61.7 (#27)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Expert14891507
GPQA Diamond—92.7%
SimpleQA Verified—47.3%

Multimodal Not comparable

Qwen3.5 Max Preview: —, Qwen3.8 Max: 37.2 (#75)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Too close to call

Qwen3.5 Max Preview: 56.2 (#22), Qwen3.8 Max: 56.7 (#18)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Non-English14651472
LMArena Chinese15341538
LMArena French14841503
LMArena German14871483
LMArena Japanese14951467
LMArena Korean14381461
LMArena Russian14711481
LMArena Spanish14701492

Instruction Following Too close to call

Qwen3.5 Max Preview: 77.0 (#31), Qwen3.8 Max: 77.6 (#17)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Instruction Following14671479

Long Context Too close to call

Qwen3.5 Max Preview: 45.2 (#45), Qwen3.8 Max: 45.6 (#31)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Longer Query14761489

Writing & Preference Qwen3.8 Max leads

Qwen3.5 Max Preview: 66.0 (#41), Qwen3.8 Max: 67.1 (#30)

BenchmarkQwen3.5 Max PreviewQwen3.8 Max
LMArena Text14701483
LMArena Creative Writing14641479
LMArena Multi-Turn14781489

Frequently asked questions

Is Qwen3.5 Max Preview better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 45.3 on the Noometry Index.

Is Qwen3.5 Max Preview or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 44.0 in the Noometry coding category.

How many benchmarks do Qwen3.5 Max Preview and Qwen3.8 Max share?

17 benchmarks have published results for both models. Qwen3.5 Max Preview has 17 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper