Noometry

Model comparison

DeepSeek-V3.2-Exp vs Qwen1.5-32B

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 30.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek-V3.2-Exp DeepSeek

44.3

Rank #78 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 8 categories and Qwen1.5-32B in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 83.4% for DeepSeek-V3.2-Exp and 30.7% for Qwen1.5-32B.

Side by side

DeepSeek-V3.2-ExpQwen1.5-32B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index44.330.5
Released2025-09-292024-02-04
WeightsOpenOpen
Context window164K—
Max output66K—
Input $ / M tokens$0.26—
Output $ / M tokens$0.38—
Results tracked4921

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

Category by category

Coding DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 46.5 (#65), Qwen1.5-32B: 31.7 (#282)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Coding14541155
SWE-bench Verified (bash only)70%—
Aider Polyglot74.2%—
LMArena WebDev1362—
SWE-bench Multilingual59%—
SciCode38.9%—
WeirdML39.5%—
BigCodeBench Instruct—32.3%
BigCodeBench Complete—42%

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 32.7 (#59), Qwen1.5-32B: —

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
Terminal-Bench39.6%—
APEX-Agents21.3%—
Berkeley Function Calling Leaderboard56.7%—
TheAgentCompany42.9%—
Vending-Bench 21,034—

Reasoning Too close to call

DeepSeek-V3.2-Exp: 22.1 (#208), Qwen1.5-32B: 21.8 (#212)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Hard Prompts14341130
ARC-AGI-24%—
Kagi LLM Benchmark52.2%—
NYT Connections (extended)36.7%—
ARC-AGI-157%—
CritPt2.9%—
Chess Puzzles14%—
Thematic Generalization65%—
DTBench87.7%—
LMCA29.1%—
Epoch Capabilities Index146.27—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 41.7 (#87), Qwen1.5-32B: 33.0 (#207)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Math14351155
MathArena Final-Answer Competitions57.7%—
OTIS Mock AIME 2024-202587.8%—
ProofBench8%—
FrontierMath (Feb 2025 set)22.1%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 51.7 (#66), Qwen1.5-32B: 13.5 (#296)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
GPQA Diamond83.4%30.7%
LMArena Expert14361126
Vectara Hallucination Rate5.3%—
MMLU—74.4%

Multilingual DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 52.2 (#90), Qwen1.5-32B: 31.4 (#259)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Non-English14091106
LMArena Chinese14611177
LMArena French14331101
LMArena German14401058
LMArena Japanese13741027
LMArena Korean13711008
LMArena Russian14241073
LMArena Spanish14401089

Instruction Following DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 74.5 (#93), Qwen1.5-32B: 57.7 (#265)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Instruction Following14131116

Long Context DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 47.6 (#16), Qwen1.5-32B: 34.7 (#246)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Longer Query14281146
Fiction.LiveBench83.3%—
CL-bench13.2%—
CL-bench Life9.5%—

Writing & Preference DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 62.4 (#77), Qwen1.5-32B: 34.2 (#271)

BenchmarkDeepSeek-V3.2-ExpQwen1.5-32B
LMArena Text14251137
LMArena Creative Writing14031083
LMArena Multi-Turn14271140
EQ-Bench Creative Writing1515—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Qwen1.5-32B?

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 30.5 on the Noometry Index.

Is DeepSeek-V3.2-Exp or Qwen1.5-32B better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 31.7 in the Noometry coding category.

How many benchmarks do DeepSeek-V3.2-Exp and Qwen1.5-32B share?

18 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper