Noometry

Model comparison

Qwen2-72B vs Qwen3.5-Flash

Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 29.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

29.5

Rank #294 Confirmed

Qwen3.5-Flash Alibaba (Qwen)

42.3

Rank #105 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 82.3% for Qwen3.5-Flash.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Qwen2-72BQwen3.5-Flash
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index29.542.3
Released2024-06-072026-02-23
WeightsOpenProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked2632

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

Category by category

Coding Qwen3.5-Flash leads

Qwen2-72B: 28.7 (#303), Qwen3.5-Flash: 33.9 (#234)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Coding11961412
LMArena WebDev—1243
WeirdML11.3%—
BigCodeBench Instruct38.5%—
BigCodeBench Complete54%—
ALE-Bench—221.8

Agentic & Tool Use Not comparable

Qwen2-72B: 16.9 (#138), Qwen3.5-Flash: —

BenchmarkQwen2-72BQwen3.5-Flash
TheAgentCompany1.1%—
METR Time Horizons29.9%—
Vending-Bench 2—462.69

Reasoning Qwen3.5-Flash leads

Qwen2-72B: 22.2 (#184), Qwen3.5-Flash: 32.9 (#63)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Hard Prompts11911404
Epoch Capabilities Index125.27143.98
Chess Puzzles—21%
Mystery Game Puzzles—20%
DTBench—82.9%
LMCA—29.1%

Math Qwen3.5-Flash leads

Qwen2-72B: 27.9 (#232), Qwen3.5-Flash: 36.3 (#117)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Math12351407
FrontierMath (Tiers 1-3)—18.2%
OTIS Mock AIME 2024-2025—84.4%
MATH Level 539.1%—
FrontierMath (Feb 2025 set)—6.2%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3.5-Flash leads

Qwen2-72B: 21.2 (#270), Qwen3.5-Flash: 43.2 (#84)

BenchmarkQwen2-72BQwen3.5-Flash
GPQA Diamond40.8%82.3%
LMArena Expert11711408
SimpleQA Verified—20.3%
Vectara Hallucination Rate—10.5%
MMLU82.4%—

Multilingual Qwen3.5-Flash leads

Qwen2-72B: 36.0 (#239), Qwen3.5-Flash: 50.7 (#116)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Non-English11761385
LMArena Chinese12401446
LMArena French11691412
LMArena German11511389
LMArena Japanese11111369
LMArena Korean10831344
LMArena Russian11691379
LMArena Spanish11681399

Instruction Following Qwen3.5-Flash leads

Qwen2-72B: 62.0 (#236), Qwen3.5-Flash: 72.8 (#133)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Instruction Following11811374

Long Context Qwen3.5-Flash leads

Qwen2-72B: 36.1 (#230), Qwen3.5-Flash: 42.4 (#119)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Longer Query11931392

Writing & Preference Qwen3.5-Flash leads

Qwen2-72B: 41.0 (#236), Qwen3.5-Flash: 58.2 (#117)

BenchmarkQwen2-72BQwen3.5-Flash
LMArena Text12031397
LMArena Creative Writing11811343
LMArena Multi-Turn11951393

Frequently asked questions

Is Qwen2-72B better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 29.5 on the Noometry Index.

Is Qwen2-72B or Qwen3.5-Flash better for coding?

Qwen3.5-Flash scores higher on coding benchmarks: 33.9 versus 28.7 in the Noometry coding category.

How many benchmarks do Qwen2-72B and Qwen3.5-Flash share?

19 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.5-Flash has 32.

Related comparisons

Go deeper