Noometry

Model comparison

DeepSeek-R1-Distill-Qwen-32B vs Qwen1.5-32B

DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 30.5 on the Noometry Index.

Last verified . 3 shared benchmarks.

DeepSeek-R1-Distill-Qwen-32B DeepSeek

35.5

Rank #226 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 3 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-32B scores higher in 5 categories and Qwen1.5-32B in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek-R1-Distill-Qwen-32B leads 35.7 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 64.1% for DeepSeek-R1-Distill-Qwen-32B and 30.7% for Qwen1.5-32B.

Side by side

DeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index35.530.5
Released2025-01-202024-02-04
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1421

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

Category by category

Coding DeepSeek-R1-Distill-Qwen-32B leads

DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212), Qwen1.5-32B: 31.7 (#282)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
BigCodeBench Instruct43.9%32.3%
BigCodeBench Complete54.9%42%
LiveBench Coding33.7%—
LMArena Coding—1155

Agentic & Tool Use Not comparable

DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94), Qwen1.5-32B: —

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
BALROG19.5%—

Reasoning Qwen1.5-32B leads

DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284), Qwen1.5-32B: 21.8 (#212)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
Chess Puzzles1%—
LiveBench Reasoning52.3%—
LMArena Hard Prompts—1130
LiveBench Data Analysis45.4%—
Epoch Capabilities Index137.44—
LiveBench45.5%—

Math DeepSeek-R1-Distill-Qwen-32B leads

DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194), Qwen1.5-32B: 33.0 (#207)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
OTIS Mock AIME 2024-202555.6%—
LiveBench Math59.4%—
LMArena Math—1155

Knowledge DeepSeek-R1-Distill-Qwen-32B leads

DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182), Qwen1.5-32B: 13.5 (#296)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
GPQA Diamond64.1%30.7%
LMArena Expert—1126
MMLU—74.4%

Multilingual Not comparable

DeepSeek-R1-Distill-Qwen-32B: —, Qwen1.5-32B: 31.4 (#259)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
LMArena Non-English—1106
LMArena Chinese—1177
LMArena French—1101
LMArena German—1058
LMArena Japanese—1027
LMArena Korean—1008
LMArena Russian—1073
LMArena Spanish—1089

Instruction Following DeepSeek-R1-Distill-Qwen-32B leads

DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243), Qwen1.5-32B: 57.7 (#265)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
LiveBench Instruction Following55.7%—
LMArena Instruction Following—1116

Long Context Not comparable

DeepSeek-R1-Distill-Qwen-32B: —, Qwen1.5-32B: 34.7 (#246)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
LMArena Longer Query—1146

Writing & Preference DeepSeek-R1-Distill-Qwen-32B leads

DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188), Qwen1.5-32B: 34.2 (#271)

BenchmarkDeepSeek-R1-Distill-Qwen-32BQwen1.5-32B
LMArena Text—1137
LMArena Creative Writing—1083
LMArena Multi-Turn—1140
LiveBench Language26.8%—

Frequently asked questions

Is DeepSeek-R1-Distill-Qwen-32B better than Qwen1.5-32B?

DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 30.5 on the Noometry Index.

Is DeepSeek-R1-Distill-Qwen-32B or Qwen1.5-32B better for coding?

DeepSeek-R1-Distill-Qwen-32B scores higher on coding benchmarks: 36.1 versus 31.7 in the Noometry coding category.

How many benchmarks do DeepSeek-R1-Distill-Qwen-32B and Qwen1.5-32B share?

3 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-32B has 14 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper