Noometry

Model comparison

Qwen2-72B vs Qwen3.6 Max Preview

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 29.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

29.5

Rank #294 Confirmed

Qwen3.6 Max Preview Alibaba (Qwen)

51.1

Rank #36 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Qwen2-72B 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 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 87.4% for Qwen3.6 Max Preview.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Qwen2-72BQwen3.6 Max Preview
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index29.551.1
Released2024-06-072026-04-20
WeightsOpenProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.30
Output $ / M tokens—$7.80
Results tracked2629

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

Category by category

Coding Qwen3.6 Max Preview leads

Qwen2-72B: 28.7 (#303), Qwen3.6 Max Preview: 48.6 (#50)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Coding11961472
SWE-bench Verified—76.7%
LMArena WebDev—1482
WeirdML11.3%—
BigCodeBench Instruct38.5%—
BigCodeBench Complete54%—

Agentic & Tool Use Not comparable

Qwen2-72B: 16.9 (#138), Qwen3.6 Max Preview: —

BenchmarkQwen2-72BQwen3.6 Max Preview
TheAgentCompany1.1%—
METR Time Horizons29.9%—
Vending-Bench 2—4,254

Reasoning Qwen3.6 Max Preview leads

Qwen2-72B: 22.2 (#184), Qwen3.6 Max Preview: 40.8 (#47)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Hard Prompts11911457
Epoch Capabilities Index125.27149.27
SimpleBench—63%
NYT Connections (extended)—74.1%
Chess Puzzles—20%
Mystery Game Puzzles—19%
DTBench—87.2%
LMCA—42.5%

Math Qwen3.6 Max Preview leads

Qwen2-72B: 27.9 (#232), Qwen3.6 Max Preview: 52.2 (#40)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Math12351465
OTIS Mock AIME 2024-2025—91.1%
MATH Level 539.1%—
FrontierMath (Feb 2025 set)—23.1%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Qwen3.6 Max Preview leads

Qwen2-72B: 21.2 (#270), Qwen3.6 Max Preview: 57.6 (#35)

BenchmarkQwen2-72BQwen3.6 Max Preview
GPQA Diamond40.8%87.4%
LMArena Expert11711476
SimpleQA Verified—52%
MMLU82.4%—

Multilingual Qwen3.6 Max Preview leads

Qwen2-72B: 36.0 (#239), Qwen3.6 Max Preview: 54.3 (#46)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Non-English11761436
LMArena Chinese12401487
LMArena French11691449
LMArena Russian11691444
LMArena Spanish11681452
LMArena German1151—
LMArena Japanese1111—
LMArena Korean1083—

Instruction Following Qwen3.6 Max Preview leads

Qwen2-72B: 62.0 (#236), Qwen3.6 Max Preview: 75.8 (#51)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Instruction Following11811437

Long Context Qwen3.6 Max Preview leads

Qwen2-72B: 36.1 (#230), Qwen3.6 Max Preview: 44.6 (#59)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Longer Query11931457

Writing & Preference Qwen3.6 Max Preview leads

Qwen2-72B: 41.0 (#236), Qwen3.6 Max Preview: 64.0 (#58)

BenchmarkQwen2-72BQwen3.6 Max Preview
LMArena Text12031447
LMArena Creative Writing11811435
LMArena Multi-Turn11951456

Frequently asked questions

Is Qwen2-72B better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 29.5 on the Noometry Index.

Is Qwen2-72B or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 28.7 in the Noometry coding category.

How many benchmarks do Qwen2-72B and Qwen3.6 Max Preview share?

16 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.6 Max Preview has 29.

Related comparisons

Go deeper