Noometry

Model comparison

gpt-oss-20b vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 32.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 21 benchmarks with published results for both. gpt-oss-20b scores higher in 2 categories and QwQ-32B in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where QwQ-32B leads 50.6 to 35.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 59.2% for QwQ-32B.

Side by side

gpt-oss-20bQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index32.539.8
Released2025-08-052024-11-28
WeightsOpenOpen
Context window131K—
Max output16K—
Input $ / M tokens$0.018—
Output $ / M tokens$0.09—
Results tracked3436

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

Category by category

Coding gpt-oss-20b leads

gpt-oss-20b: 37.6 (#192), QwQ-32B: 35.4 (#226)

Benchmarkgpt-oss-20bQwQ-32B
LMArena Coding13061333
Aider Polyglot—20.9%
SciCode34.4%—
WeirdML40.9%—
BigCodeBench Instruct—44.6%
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%
ALE-Bench566.05—

Agentic & Tool Use Not comparable

gpt-oss-20b: 9.3 (#154), QwQ-32B: —

Benchmarkgpt-oss-20bQwQ-32B
Terminal-Bench3.4%—

Reasoning QwQ-32B leads

gpt-oss-20b: 19.3 (#261), QwQ-32B: 23.7 (#174)

Benchmarkgpt-oss-20bQwQ-32B
Chess Puzzles4%5%
LMArena Hard Prompts12741325
Epoch Capabilities Index137.82137.6
Kagi LLM Benchmark53.2%—
CritPt1.4%—
LiveBench Reasoning—83.5%
DTBench68%—
LiveBench Data Analysis—65%
LMCA14.5%—
ForecastBench—58.3
LiveBench—72%

Math gpt-oss-20b leads

gpt-oss-20b: 39.4 (#103), QwQ-32B: 38.0 (#143)

Benchmarkgpt-oss-20bQwQ-32B
OTIS Mock AIME 2024-202565.3%59.2%
LMArena Math13171359
Omni-MATH56.5%—
LiveBench Math—77.8%

Knowledge QwQ-32B leads

gpt-oss-20b: 34.6 (#195), QwQ-32B: 37.2 (#158)

Benchmarkgpt-oss-20bQwQ-32B
GPQA Diamond60.8%65.3%
LMArena Expert12581324
MMLU-Pro74%—
Confabulations—15.6%
GPQA (HELM)59.4%—

Multilingual QwQ-32B leads

gpt-oss-20b: 42.2 (#197), QwQ-32B: 44.8 (#176)

Benchmarkgpt-oss-20bQwQ-32B
LMArena Non-English12681305
LMArena Chinese13141378
LMArena German12551313
LMArena Japanese12441262
LMArena Korean12361279
LMArena Russian12781297
LMArena Spanish12671354
LMArena French—1336

Instruction Following QwQ-32B leads

gpt-oss-20b: 61.8 (#240), QwQ-32B: 72.6 (#137)

Benchmarkgpt-oss-20bQwQ-32B
LMArena Instruction Following12361297
LiveBench Instruction Following—81.8%
IFEval73.2%—

Long Context QwQ-32B leads

gpt-oss-20b: 37.9 (#209), QwQ-32B: 49.0 (#11)

Benchmarkgpt-oss-20bQwQ-32B
LMArena Longer Query12501308
Fiction.LiveBench—83.3%

Writing & Preference QwQ-32B leads

gpt-oss-20b: 35.5 (#265), QwQ-32B: 50.6 (#180)

Benchmarkgpt-oss-20bQwQ-32B
LMArena Text12871329
LMArena Creative Writing12011288
EQ-Bench Creative Writing6661257
LMArena Multi-Turn12681314
Short-Story Creative Writing—80.2%
WildBench73.7%—
LiveBench Language—51.4%

Frequently asked questions

Is gpt-oss-20b better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 32.5 on the Noometry Index.

Is gpt-oss-20b or QwQ-32B better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 35.4 in the Noometry coding category.

How many benchmarks do gpt-oss-20b and QwQ-32B share?

21 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper