Noometry

Model comparison

Qwen2-72B vs Qwen3.6 Flash

Qwen3.6 Flash is the stronger model overall, scoring 38.4 to 29.5 on the Noometry Index.

Last verified . 2 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

29.5

Rank #294 Confirmed

Qwen3.6 Flash Alibaba (Qwen)

38.4

Rank #176 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.6 Flash in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.6 Flash leads 42.2 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 83.3% for Qwen3.6 Flash.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Qwen2-72BQwen3.6 Flash
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index29.538.4
Released2024-06-072026-04-27
WeightsOpenProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.19
Output $ / M tokens—$1.13
Results tracked2613

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

Category by category

Coding Not comparable

Qwen2-72B: 28.7 (#303), Qwen3.6 Flash: —

BenchmarkQwen2-72BQwen3.6 Flash
WeirdML11.3%—
BigCodeBench Instruct38.5%—
LMArena Coding1196—
BigCodeBench Complete54%—
ALE-Bench—326.4

Agentic & Tool Use Not comparable

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

BenchmarkQwen2-72BQwen3.6 Flash
TheAgentCompany1.1%—
METR Time Horizons29.9%—

Reasoning Qwen3.6 Flash leads

Qwen2-72B: 22.2 (#184), Qwen3.6 Flash: 28.4 (#90)

BenchmarkQwen2-72BQwen3.6 Flash
Epoch Capabilities Index125.27143.26
SimpleBench—35.2%
Chess Puzzles—20%
LMArena Hard Prompts1191—
Mystery Game Puzzles—18%
DTBench—77.1%
LMCA—31%

Math Qwen3.6 Flash leads

Qwen2-72B: 27.9 (#232), Qwen3.6 Flash: 38.0 (#88)

BenchmarkQwen2-72BQwen3.6 Flash
FrontierMath (Tiers 1-3)—22.5%
OTIS Mock AIME 2024-2025—84.4%
LMArena Math1235—
MATH Level 539.1%—
FrontierMath (Feb 2025 set)—10.3%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3.6 Flash leads

Qwen2-72B: 21.2 (#270), Qwen3.6 Flash: 42.2 (#90)

BenchmarkQwen2-72BQwen3.6 Flash
GPQA Diamond40.8%83.3%
SimpleQA Verified—15.9%
LMArena Expert1171—
MMLU82.4%—

Multilingual Not comparable

Qwen2-72B: 36.0 (#239), Qwen3.6 Flash: —

BenchmarkQwen2-72BQwen3.6 Flash
LMArena Non-English1176—
LMArena Chinese1240—
LMArena French1169—
LMArena German1151—
LMArena Japanese1111—
LMArena Korean1083—
LMArena Russian1169—
LMArena Spanish1168—

Instruction Following Not comparable

Qwen2-72B: 62.0 (#236), Qwen3.6 Flash: —

BenchmarkQwen2-72BQwen3.6 Flash
LMArena Instruction Following1181—

Long Context Not comparable

Qwen2-72B: 36.1 (#230), Qwen3.6 Flash: —

BenchmarkQwen2-72BQwen3.6 Flash
LMArena Longer Query1193—

Writing & Preference Not comparable

Qwen2-72B: 41.0 (#236), Qwen3.6 Flash: —

BenchmarkQwen2-72BQwen3.6 Flash
LMArena Text1203—
LMArena Creative Writing1181—
LMArena Multi-Turn1195—

Frequently asked questions

Is Qwen2-72B better than Qwen3.6 Flash?

Qwen3.6 Flash is the stronger model overall, scoring 38.4 to 29.5 on the Noometry Index.

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

2 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.6 Flash has 13.

Related comparisons

Go deeper