Noometry

Model comparison

Qwen3 235B-A22B vs Qwen3.5 Max Preview

Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 43.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Qwen3.5 Max Preview Alibaba (Qwen)

45.3

Rank #71 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 4 categories and Qwen3.5 Max Preview in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.5 Max Preview leads 30.8 to 15.7.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

Qwen3 235B-A22BQwen3.5 Max Preview
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index43.545.3
Released2025-04—
WeightsOpenProprietary
Context window131K—
Max output16K—
Input $ / M tokens$0.70—
Output $ / M tokens$2.80—
Results tracked4917

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

Category by category

Coding Too close to call

Qwen3 235B-A22B: 44.3 (#75), Qwen3.5 Max Preview: 44.0 (#77)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Coding14451487
Aider Polyglot59.6%—
SciCode42.4%—
WeirdML41%—

Agentic & Tool Use Not comparable

Qwen3 235B-A22B: 33.9 (#51), Qwen3.5 Max Preview: —

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
Berkeley Function Calling Leaderboard52.1%—
Vending-Bench 2-11.34—

Reasoning Qwen3.5 Max Preview leads

Qwen3 235B-A22B: 15.7 (#311), Qwen3.5 Max Preview: 30.8 (#84)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Hard Prompts14331483
ARC-AGI-21.3%—
SimpleBench31%—
Kagi LLM Benchmark69.4%—
ARC-AGI-111%—
CritPt0%—
Chess Puzzles12%—
Mystery Game Puzzles9%—
DTBench80.3%—
LMCA29.3%—
Epoch Capabilities Index143.85—
ForecastBench59.7—

Math Qwen3 235B-A22B leads

Qwen3 235B-A22B: 50.4 (#57), Qwen3.5 Max Preview: 40.1 (#94)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Math14321474
OTIS Mock AIME 2024-202586.7%—
Omni-MATH71.8%—
MATH Level 568.9%—
FrontierMath (Feb 2025 set)8.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge Qwen3 235B-A22B leads

Qwen3 235B-A22B: 49.6 (#73), Qwen3.5 Max Preview: 41.8 (#107)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Expert14631489
GPQA Diamond80.1%—
SimpleQA Verified40.4%—
MMLU-Pro84.4%—
Confabulations15.6%—
Vectara Hallucination Rate9.3%—
GPQA (HELM)72.7%—

Multilingual Qwen3.5 Max Preview leads

Qwen3 235B-A22B: 52.3 (#89), Qwen3.5 Max Preview: 56.2 (#22)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Non-English14091465
LMArena Chinese14811534
LMArena French14451484
LMArena German14331487
LMArena Japanese13991495
LMArena Korean13911438
LMArena Russian14111471
LMArena Spanish14301470

Instruction Following Qwen3.5 Max Preview leads

Qwen3 235B-A22B: 72.6 (#136), Qwen3.5 Max Preview: 77.0 (#31)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Instruction Following14081467
IFEval83.5%—

Long Context Too close to call

Qwen3 235B-A22B: 46.1 (#26), Qwen3.5 Max Preview: 45.2 (#45)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Longer Query14261476
Fiction.LiveBench75%—

Writing & Preference Qwen3.5 Max Preview leads

Qwen3 235B-A22B: 59.6 (#108), Qwen3.5 Max Preview: 66.0 (#41)

BenchmarkQwen3 235B-A22BQwen3.5 Max Preview
LMArena Text14191470
LMArena Creative Writing13841464
LMArena Multi-Turn14321478
Short-Story Creative Writing83%—
EQ-Bench Creative Writing1366—
WildBench86.6%—

Frequently asked questions

Is Qwen3 235B-A22B better than Qwen3.5 Max Preview?

Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 43.5 on the Noometry Index.

Is Qwen3 235B-A22B or Qwen3.5 Max Preview better for coding?

They score almost the same on coding (44.3 vs 44.0); test both on your own repository before choosing.

How many benchmarks do Qwen3 235B-A22B and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Qwen3.5 Max Preview has 17.

Related comparisons

Go deeper