Noometry

Model comparison

DeepSeek V4 Flash vs Qwen1.5-32B

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 30.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #32 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.0

Rank #288 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek V4 Flash leads 55.5 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 91% for DeepSeek V4 Flash and 30.7% for Qwen1.5-32B.

Side by side

DeepSeek V4 FlashQwen1.5-32B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index53.630.0
Released2026-04-242024-02-04
WeightsOpenOpen
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked4121

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.6 (#56), Qwen1.5-32B: 31.1 (#278)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Coding14571155
FrontierCode18.8%—
LMArena WebDev1581—
SciCode49.9%—
WeirdML63%—
BigCodeBench Instruct—32.3%
BigCodeBench Complete—42%
ALE-Bench1,306—

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#25), Qwen1.5-32B: 20.9 (#210)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Hard Prompts14431131
ARC-AGI-261.4%—
SimpleBench61.1%—
Kagi LLM Benchmark52.2%—
NYT Connections (extended)89.6%—
ARC-AGI-189%—
CritPt16.6%—
Chess Puzzles33%—
Mystery Game Puzzles34%—
DTBench90.9%—
LMCA41.7%—
Epoch Capabilities Index154.51—

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.0 (#31), Qwen1.5-32B: 30.5 (#207)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Math14271155
FrontierMath (Tiers 1-3)57.5%—
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
OTIS Mock AIME 2024-202594.4%—
ProofBench56%—

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.5 (#43), Qwen1.5-32B: 13.5 (#291)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
GPQA Diamond91%30.7%
LMArena Expert14411126
SimpleQA Verified33.6%—
MMLU—74.4%

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.2 (#71), Qwen1.5-32B: 31.6 (#254)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Non-English14201106
LMArena Chinese14671176
LMArena French14381100
LMArena German14181058
LMArena Japanese14031027
LMArena Korean13831007
LMArena Russian14281073
LMArena Spanish14371089

Instruction Following DeepSeek V4 Flash leads

DeepSeek V4 Flash: 75.1 (#76), Qwen1.5-32B: 58.0 (#260)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Instruction Following14211116

Long Context DeepSeek V4 Flash leads

DeepSeek V4 Flash: 43.8 (#81), Qwen1.5-32B: 34.7 (#241)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Longer Query14351146

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 64.0 (#59), Qwen1.5-32B: 34.4 (#266)

BenchmarkDeepSeek V4 FlashQwen1.5-32B
LMArena Text14321137
LMArena Creative Writing14031083
LMArena Multi-Turn14491140
EQ-Bench Creative Writing1559—

Frequently asked questions

Is DeepSeek V4 Flash better than Qwen1.5-32B?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 30.0 on the Noometry Index.

Is DeepSeek V4 Flash or Qwen1.5-32B better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 31.1 in the Noometry coding category.

How many benchmarks do DeepSeek V4 Flash and Qwen1.5-32B share?

18 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper