Noometry

Model comparison

Qwen2-72B vs Qwen3.7 Plus

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 30.0 on the Noometry Index.

Last verified . 19 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.7 Plus in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 87.9% for Qwen3.7 Plus.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Qwen2-72BQwen3.7 Plus
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.045.3
Released2024-06-072026-06-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$0.40
Output $ / M tokens—$1.60
Results tracked2632

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

Category by category

Coding Qwen3.7 Plus leads

Qwen2-72B: 29.1 (#310), Qwen3.7 Plus: 36.6 (#206)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Coding11961473
FrontierCode—10.2%
SciCode—45.5%
WeirdML11.3%—
BigCodeBench Instruct38.5%—
BigCodeBench Complete54%—

Agentic & Tool Use Qwen3.7 Plus leads

Qwen2-72B: 17.0 (#146), Qwen3.7 Plus: 21.4 (#138)

BenchmarkQwen2-72BQwen3.7 Plus
OSWorld 2.0—2.8%
TheAgentCompany1.1%—
METR Time Horizons29.9%—

Reasoning Qwen3.7 Plus leads

Qwen2-72B: 23.2 (#181), Qwen3.7 Plus: 39.3 (#59)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Hard Prompts11911460
Epoch Capabilities Index125.28147.37
NYT Connections (extended)—74.8%
CritPt—9.1%
Chess Puzzles—24%
Mystery Game Puzzles—17%
DTBench—84%
LMCA—37.6%

Math Qwen3.7 Plus leads

Qwen2-72B: 30.2 (#236), Qwen3.7 Plus: 50.5 (#56)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Math12351466
FrontierMath (Tiers 1-3)—34.4%
OTIS Mock AIME 2024-2025—93.3%
MATH Level 539.1%—

Knowledge Qwen3.7 Plus leads

Qwen2-72B: 21.2 (#275), Qwen3.7 Plus: 54.9 (#51)

BenchmarkQwen2-72BQwen3.7 Plus
GPQA Diamond40.8%87.9%
LMArena Expert11711467
MMLU82.4%—

Multimodal Not comparable

Qwen2-72B: —, Qwen3.7 Plus: 41.8 (#33)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Vision—1279
LMArena Document—1444

Multilingual Qwen3.7 Plus leads

Qwen2-72B: 35.9 (#244), Qwen3.7 Plus: 54.8 (#38)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Non-English11761445
LMArena Chinese12401510
LMArena French11701473
LMArena German11511471
LMArena Japanese11111413
LMArena Korean10831415
LMArena Russian11691457
LMArena Spanish11691457

Instruction Following Qwen3.7 Plus leads

Qwen2-72B: 61.7 (#241), Qwen3.7 Plus: 75.8 (#52)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Instruction Following11811440

Long Context Qwen3.7 Plus leads

Qwen2-72B: 36.1 (#235), Qwen3.7 Plus: 44.5 (#65)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Longer Query11921455

Writing & Preference Qwen3.7 Plus leads

Qwen2-72B: 40.8 (#241), Qwen3.7 Plus: 64.3 (#56)

BenchmarkQwen2-72BQwen3.7 Plus
LMArena Text12031455
LMArena Creative Writing11811439
LMArena Multi-Turn11961460

Frequently asked questions

Is Qwen2-72B better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 30.0 on the Noometry Index.

Is Qwen2-72B or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 29.1 in the Noometry coding category.

How many benchmarks do Qwen2-72B and Qwen3.7 Plus share?

19 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.7 Plus has 32.

Related comparisons

Go deeper