Noometry

Model comparison

Qwen2-72B vs Qwen3.7 Flash

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 30.0 on the Noometry Index.

Last verified . 2 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Qwen3.7 Flash Alibaba (Qwen)

39.9

Rank #156 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.7 Flash in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.7 Flash leads 48.9 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 82.3% for Qwen3.7 Flash.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Qwen2-72BQwen3.7 Flash
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.039.9
Released2024-06-072026-07-15
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$0.03
Output $ / M tokens—$0.13
Results tracked267

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

Category by category

Coding Not comparable

Qwen2-72B: 29.1 (#310), Qwen3.7 Flash: —

BenchmarkQwen2-72BQwen3.7 Flash
WeirdML11.3%—
BigCodeBench Instruct38.5%—
LMArena Coding1196—
BigCodeBench Complete54%—

Agentic & Tool Use Not comparable

Qwen2-72B: 17.0 (#146), Qwen3.7 Flash: —

BenchmarkQwen2-72BQwen3.7 Flash
TheAgentCompany1.1%—
METR Time Horizons29.9%—

Reasoning Qwen3.7 Flash leads

Qwen2-72B: 23.2 (#181), Qwen3.7 Flash: 28.2 (#108)

BenchmarkQwen2-72BQwen3.7 Flash
Epoch Capabilities Index125.28144.64
NYT Connections (extended)—43.8%
Chess Puzzles—23%
LMArena Hard Prompts1191—
Mystery Game Puzzles—15%

Math Qwen3.7 Flash leads

Qwen2-72B: 30.2 (#236), Qwen3.7 Flash: 38.3 (#140)

BenchmarkQwen2-72BQwen3.7 Flash
FrontierMath (Tiers 1-3)—19.3%
OTIS Mock AIME 2024-2025—86.7%
LMArena Math1235—
MATH Level 539.1%—

Knowledge Qwen3.7 Flash leads

Qwen2-72B: 21.2 (#275), Qwen3.7 Flash: 48.9 (#75)

BenchmarkQwen2-72BQwen3.7 Flash
GPQA Diamond40.8%82.3%
LMArena Expert1171—
MMLU82.4%—

Multilingual Not comparable

Qwen2-72B: 35.9 (#244), Qwen3.7 Flash: —

BenchmarkQwen2-72BQwen3.7 Flash
LMArena Non-English1176—
LMArena Chinese1240—
LMArena French1170—
LMArena German1151—
LMArena Japanese1111—
LMArena Korean1083—
LMArena Russian1169—
LMArena Spanish1169—

Instruction Following Not comparable

Qwen2-72B: 61.7 (#241), Qwen3.7 Flash: —

BenchmarkQwen2-72BQwen3.7 Flash
LMArena Instruction Following1181—

Long Context Not comparable

Qwen2-72B: 36.1 (#235), Qwen3.7 Flash: —

BenchmarkQwen2-72BQwen3.7 Flash
LMArena Longer Query1192—

Writing & Preference Not comparable

Qwen2-72B: 40.8 (#241), Qwen3.7 Flash: —

BenchmarkQwen2-72BQwen3.7 Flash
LMArena Text1203—
LMArena Creative Writing1181—
LMArena Multi-Turn1196—

Frequently asked questions

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

Qwen3.7 Flash is the stronger model overall, scoring 39.9 to 30.0 on the Noometry Index.

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

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

Related comparisons

Go deeper