Noometry

Model comparison

gpt-oss-120b vs Qwen1.5-32B

gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 18 benchmarks with published results for both. gpt-oss-120b scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where gpt-oss-120b leads 42.4 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 75.8% for gpt-oss-120b and 30.7% for Qwen1.5-32B.

Side by side

gpt-oss-120bQwen1.5-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.330.5
Released2025-08-052024-02-04
WeightsOpenOpen
Context window131K—
Max output41K—
Input $ / M tokens$0.037—
Output $ / M tokens$0.17—
Results tracked4821

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

Category by category

Coding gpt-oss-120b leads

gpt-oss-120b: 33.5 (#256), Qwen1.5-32B: 31.7 (#282)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Coding13801155
SWE-bench Verified (bash only)26%—
Aider Polyglot41.8%—
SciCode36%—
WeirdML48.2%—
BigCodeBench Instruct—32.3%
BigCodeBench Complete—42%
ALE-Bench575.62—
AlgoTune1.41—

Agentic & Tool Use Not comparable

gpt-oss-120b: 12.2 (#153), Qwen1.5-32B: —

Benchmarkgpt-oss-120bQwen1.5-32B
Terminal-Bench18.7%—
APEX-Agents4.4%—
METR Time Horizons56.6%—
Vending-Bench 2-21.53—

Reasoning Qwen1.5-32B leads

gpt-oss-120b: 20.0 (#245), Qwen1.5-32B: 21.8 (#212)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Hard Prompts13641130
SimpleBench22.1%—
Kagi LLM Benchmark58.6%—
CritPt1.1%—
Chess Puzzles20%—
Mystery Game Puzzles2%—
DTBench76.3%—
LMCA22.1%—
Surface Evolver Bench25%—
Epoch Capabilities Index139.93—

Math gpt-oss-120b leads

gpt-oss-120b: 52.5 (#50), Qwen1.5-32B: 33.0 (#207)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Math13891155
OTIS Mock AIME 2024-202588.9%—
Omni-MATH68.8%—

Knowledge gpt-oss-120b leads

gpt-oss-120b: 42.4 (#96), Qwen1.5-32B: 13.5 (#296)

Benchmarkgpt-oss-120bQwen1.5-32B
GPQA Diamond75.8%30.7%
LMArena Expert13561126
MMLU-Pro79.5%—
Confabulations15.7%—
Vectara Hallucination Rate14.2%—
GPQA (HELM)68.4%—
MMLU—74.4%

Multilingual gpt-oss-120b leads

gpt-oss-120b: 48.0 (#147), Qwen1.5-32B: 31.4 (#259)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Non-English13511106
LMArena Chinese13851177
LMArena French13691101
LMArena German13531058
LMArena Japanese13311027
LMArena Korean12821008
LMArena Russian13431073
LMArena Spanish13891089

Instruction Following gpt-oss-120b leads

gpt-oss-120b: 69.3 (#173), Qwen1.5-32B: 57.7 (#265)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Instruction Following13181116
IFEval83.6%—

Long Context Qwen1.5-32B leads

gpt-oss-120b: 31.4 (#278), Qwen1.5-32B: 34.7 (#246)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Longer Query13191146
Fiction.LiveBench44.4%—

Writing & Preference gpt-oss-120b leads

gpt-oss-120b: 46.5 (#217), Qwen1.5-32B: 34.2 (#271)

Benchmarkgpt-oss-120bQwen1.5-32B
LMArena Text13651137
LMArena Creative Writing12751083
LMArena Multi-Turn13401140
Short-Story Creative Writing77.1%—
EQ-Bench Creative Writing961—
WildBench84.5%—

Frequently asked questions

Is gpt-oss-120b better than Qwen1.5-32B?

gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.5 on the Noometry Index.

Is gpt-oss-120b or Qwen1.5-32B better for coding?

gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 31.7 in the Noometry coding category.

How many benchmarks do gpt-oss-120b and Qwen1.5-32B share?

18 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper