Noometry

Model comparison

Qwen3.7 Max vs WizardLM-2 8x22B

Qwen3.7 Max has enough public results to be ranked (#35); WizardLM-2 8x22B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Qwen3.7 Max Alibaba (Qwen)

51.4

Rank #35 Confirmed

WizardLM-2 8x22B Microsoft

30.7

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Qwen3.7 Max scores higher in 2 categories and WizardLM-2 8x22B in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.7 Max leads 61.7 to 23.3.
  • The biggest single-benchmark swing is GPQA Diamond: 90.9% for Qwen3.7 Max and 43.4% for WizardLM-2 8x22B.
  • WizardLM-2 8x22B is cheaper at $0.62 / $0.62 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
  • Qwen3.7 Max accepts more context: 1M tokens versus 66K.
  • WizardLM-2 8x22B has downloadable open weights; the other is API-only.

Side by side

Qwen3.7 MaxWizardLM-2 8x22B
ProviderAlibaba (Qwen)Microsoft
Noometry Index51.430.7
Released2026-05-192024-04-15
WeightsProprietaryOpen
Context window1M66K
Max output131K8K
Input $ / M tokens$2.50$0.62
Output $ / M tokens$7.50$0.62
Results tracked332

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

Category by category

Coding Not comparable

Qwen3.7 Max: 50.2 (#43), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
SWE-bench Verified77.3%—
LMArena WebDev1515—
SciCode48.8%—
LMArena Coding1498—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

Qwen3.7 Max: 21.8 (#129), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
GBAEval0.4%—

Reasoning Not comparable

Qwen3.7 Max: 48.4 (#36), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
SimpleBench70.4%—
NYT Connections (extended)85.1%—
CritPt13.4%—
Chess Puzzles19%—
EBR-Bench9.5%—
LMArena Hard Prompts1483—
Mystery Game Puzzles32%—
DTBench92.3%—
LMCA44%—
Epoch Capabilities Index153.74—

Math Qwen3.7 Max leads

Qwen3.7 Max: 62.3 (#26), WizardLM-2 8x22B: 26.8

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
FrontierMath (Tiers 1-3)64.6%—
FrontierMath Tier 434.1%—
OTIS Mock AIME 2024-202595.6%—
ProofBench26%—
LMArena Math1488—
MATH Level 5—25.7%

Knowledge Qwen3.7 Max leads

Qwen3.7 Max: 61.7 (#24), WizardLM-2 8x22B: 23.3

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
GPQA Diamond90.9%43.4%
SimpleQA Verified55.8%—
LMArena Expert1488—

Multilingual Not comparable

Qwen3.7 Max: 57.1 (#13), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
LMArena Non-English1475—
LMArena Chinese1533—
LMArena Russian1482—

Instruction Following Not comparable

Qwen3.7 Max: 76.9 (#34), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
LMArena Instruction Following1460—

Long Context Not comparable

Qwen3.7 Max: 45.4 (#34), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
LMArena Longer Query1484—

Writing & Preference Not comparable

Qwen3.7 Max: 65.2 (#52), WizardLM-2 8x22B: —

BenchmarkQwen3.7 MaxWizardLM-2 8x22B
LMArena Text1476—
LMArena Creative Writing1450—
EQ-Bench 41110—
LMArena Multi-Turn1482—

Frequently asked questions

Is Qwen3.7 Max better than WizardLM-2 8x22B?

Qwen3.7 Max has enough public results to be ranked (#35); WizardLM-2 8x22B does not yet, so treat this comparison as directional.

Which is cheaper, Qwen3.7 Max or WizardLM-2 8x22B?

WizardLM-2 8x22B is cheaper. It lists at $0.62 per million input tokens and $0.62 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 66K.

How many benchmarks do Qwen3.7 Max and WizardLM-2 8x22B share?

1 benchmark has published results for both models. Qwen3.7 Max has 33 scored results on Noometry and WizardLM-2 8x22B has 2.

Related comparisons

Go deeper