Noometry

Model comparison

DeepSeek V4.1 Flash vs Qwen1.5-72B

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek V4.1 Flash leads 57.9 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 89.8% for DeepSeek V4.1 Flash and 28.8% for Qwen1.5-72B.

Side by side

DeepSeek V4.1 FlashQwen1.5-72B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index52.830.8
Released2026-09-092024-02-04
WeightsOpenOpen
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3722

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Qwen1.5-72B: 31.9 (#277)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Coding15061165
LMArena WebDev1619—
SciCode51.9%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench1,092—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Qwen1.5-72B: —

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Qwen1.5-72B: 22.2 (#203)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Hard Prompts14831148
NYT Connections (extended)89.6%—
CritPt14.3%—
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Qwen1.5-72B: 33.2 (#205)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Math14771164
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Qwen1.5-72B: 11.5 (#300)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
GPQA Diamond89.8%28.8%
LMArena Expert15061136

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Qwen1.5-72B: —

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Qwen1.5-72B: 33.2 (#253)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Non-English14481135
LMArena Chinese14971186
LMArena French14521159
LMArena German14841084
LMArena Japanese14121061
LMArena Korean14521050
LMArena Russian14711104
LMArena Spanish14591110

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Qwen1.5-72B: 59.3 (#256)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Instruction Following14741141

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Qwen1.5-72B: 35.1 (#243)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Longer Query14751157

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Qwen1.5-72B: 37.3 (#258)

BenchmarkDeepSeek V4.1 FlashQwen1.5-72B
LMArena Text14621166
LMArena Creative Writing14351137
LMArena Multi-Turn14571160
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Qwen1.5-72B?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.8 on the Noometry Index.

Is DeepSeek V4.1 Flash or Qwen1.5-72B better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek V4.1 Flash and Qwen1.5-72B share?

18 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper