Noometry

Model comparison

gpt-oss-120b vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 36.3 on the Noometry Index.

Last verified . 26 shared benchmarks.

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 26 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and QwQ-32B in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where QwQ-32B leads 49.0 to 31.4.
  • The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for gpt-oss-120b and 83.3% for QwQ-32B.

Side by side

gpt-oss-120bQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.339.8
Released2025-08-052024-11-28
WeightsOpenOpen
Context window131K—
Max output41K—
Input $ / M tokens$0.037—
Output $ / M tokens$0.17—
Results tracked4836

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

Category by category

Coding QwQ-32B leads

gpt-oss-120b: 33.5 (#256), QwQ-32B: 35.4 (#226)

Benchmarkgpt-oss-120bQwQ-32B
Aider Polyglot41.8%20.9%
LMArena Coding13801333
SWE-bench Verified (bash only)26%—
SciCode36%—
WeirdML48.2%—
BigCodeBench Instruct—44.6%
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%
ALE-Bench575.62—
AlgoTune1.41—

Agentic & Tool Use Not comparable

gpt-oss-120b: 12.2 (#153), QwQ-32B: —

Benchmarkgpt-oss-120bQwQ-32B
Terminal-Bench18.7%—
APEX-Agents4.4%—
METR Time Horizons56.6%—
Vending-Bench 2-21.53—

Reasoning QwQ-32B leads

gpt-oss-120b: 20.0 (#245), QwQ-32B: 23.7 (#174)

Benchmarkgpt-oss-120bQwQ-32B
Chess Puzzles20%5%
LMArena Hard Prompts13641325
Epoch Capabilities Index139.93137.6
SimpleBench22.1%—
Kagi LLM Benchmark58.6%—
CritPt1.1%—
LiveBench Reasoning—83.5%
Mystery Game Puzzles2%—
DTBench76.3%—
LiveBench Data Analysis—65%
LMCA22.1%—
Surface Evolver Bench25%—
ForecastBench—58.3
LiveBench—72%

Math gpt-oss-120b leads

gpt-oss-120b: 52.5 (#50), QwQ-32B: 38.0 (#143)

Benchmarkgpt-oss-120bQwQ-32B
OTIS Mock AIME 2024-202588.9%59.2%
LMArena Math13891359
Omni-MATH68.8%—
LiveBench Math—77.8%

Knowledge gpt-oss-120b leads

gpt-oss-120b: 42.4 (#96), QwQ-32B: 37.2 (#158)

Benchmarkgpt-oss-120bQwQ-32B
GPQA Diamond75.8%65.3%
Confabulations15.7%15.6%
LMArena Expert13561324
MMLU-Pro79.5%—
Vectara Hallucination Rate14.2%—
GPQA (HELM)68.4%—

Multilingual gpt-oss-120b leads

gpt-oss-120b: 48.0 (#147), QwQ-32B: 44.8 (#176)

Benchmarkgpt-oss-120bQwQ-32B
LMArena Non-English13511305
LMArena Chinese13851378
LMArena French13691336
LMArena German13531313
LMArena Japanese13311262
LMArena Korean12821279
LMArena Russian13431297
LMArena Spanish13891354

Instruction Following QwQ-32B leads

gpt-oss-120b: 69.3 (#173), QwQ-32B: 72.6 (#137)

Benchmarkgpt-oss-120bQwQ-32B
LMArena Instruction Following13181297
LiveBench Instruction Following—81.8%
IFEval83.6%—

Long Context QwQ-32B leads

gpt-oss-120b: 31.4 (#278), QwQ-32B: 49.0 (#11)

Benchmarkgpt-oss-120bQwQ-32B
Fiction.LiveBench44.4%83.3%
LMArena Longer Query13191308

Writing & Preference QwQ-32B leads

gpt-oss-120b: 46.5 (#217), QwQ-32B: 50.6 (#180)

Benchmarkgpt-oss-120bQwQ-32B
LMArena Text13651329
LMArena Creative Writing12751288
Short-Story Creative Writing77.1%80.2%
EQ-Bench Creative Writing9611257
LMArena Multi-Turn13401314
WildBench84.5%—
LiveBench Language—51.4%

Frequently asked questions

Is gpt-oss-120b better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 36.3 on the Noometry Index.

Is gpt-oss-120b or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 35.4 versus 33.5 in the Noometry coding category.

How many benchmarks do gpt-oss-120b and QwQ-32B share?

26 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper