Noometry

Model comparison

gpt-oss-120b vs Qwen3.5 Max Preview

Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 36.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Qwen3.5 Max Preview Alibaba (Qwen)

45.3

Rank #71 Confirmed

Summary

  • They share 17 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Qwen3.5 Max Preview in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3.5 Max Preview leads 66.0 to 46.5.
  • gpt-oss-120b has downloadable open weights; the other is API-only.

Side by side

gpt-oss-120bQwen3.5 Max Preview
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.345.3
Released2025-08-05—
WeightsOpenProprietary
Context window131K—
Max output41K—
Input $ / M tokens$0.037—
Output $ / M tokens$0.17—
Results tracked4817

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

Category by category

Coding Qwen3.5 Max Preview leads

gpt-oss-120b: 33.5 (#256), Qwen3.5 Max Preview: 44.0 (#77)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Coding13801487
SWE-bench Verified (bash only)26%—
Aider Polyglot41.8%—
SciCode36%—
WeirdML48.2%—
ALE-Bench575.62—
AlgoTune1.41—

Agentic & Tool Use Not comparable

gpt-oss-120b: 12.2 (#153), Qwen3.5 Max Preview: —

Benchmarkgpt-oss-120bQwen3.5 Max Preview
Terminal-Bench18.7%—
APEX-Agents4.4%—
METR Time Horizons56.6%—
Vending-Bench 2-21.53—

Reasoning Qwen3.5 Max Preview leads

gpt-oss-120b: 20.0 (#245), Qwen3.5 Max Preview: 30.8 (#84)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Hard Prompts13641483
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), Qwen3.5 Max Preview: 40.1 (#94)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Math13891474
OTIS Mock AIME 2024-202588.9%—
Omni-MATH68.8%—

Knowledge Too close to call

gpt-oss-120b: 42.4 (#96), Qwen3.5 Max Preview: 41.8 (#107)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Expert13561489
GPQA Diamond75.8%—
MMLU-Pro79.5%—
Confabulations15.7%—
Vectara Hallucination Rate14.2%—
GPQA (HELM)68.4%—

Multilingual Qwen3.5 Max Preview leads

gpt-oss-120b: 48.0 (#147), Qwen3.5 Max Preview: 56.2 (#22)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Non-English13511465
LMArena Chinese13851534
LMArena French13691484
LMArena German13531487
LMArena Japanese13311495
LMArena Korean12821438
LMArena Russian13431471
LMArena Spanish13891470

Instruction Following Qwen3.5 Max Preview leads

gpt-oss-120b: 69.3 (#173), Qwen3.5 Max Preview: 77.0 (#31)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Instruction Following13181467
IFEval83.6%—

Long Context Qwen3.5 Max Preview leads

gpt-oss-120b: 31.4 (#278), Qwen3.5 Max Preview: 45.2 (#45)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Longer Query13191476
Fiction.LiveBench44.4%—

Writing & Preference Qwen3.5 Max Preview leads

gpt-oss-120b: 46.5 (#217), Qwen3.5 Max Preview: 66.0 (#41)

Benchmarkgpt-oss-120bQwen3.5 Max Preview
LMArena Text13651470
LMArena Creative Writing12751464
LMArena Multi-Turn13401478
Short-Story Creative Writing77.1%—
EQ-Bench Creative Writing961—
WildBench84.5%—

Frequently asked questions

Is gpt-oss-120b better than Qwen3.5 Max Preview?

Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 36.3 on the Noometry Index.

Is gpt-oss-120b or Qwen3.5 Max Preview better for coding?

Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 33.5 in the Noometry coding category.

How many benchmarks do gpt-oss-120b and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen3.5 Max Preview has 17.

Related comparisons

Go deeper