Noometry

Model comparison

gpt-oss-20b vs Qwen2.5-Max

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 32.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 17 benchmarks with published results for both. gpt-oss-20b scores higher in 1 category and Qwen2.5-Max in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen2.5-Max leads 55.4 to 35.5.
  • gpt-oss-20b has downloadable open weights; the other is API-only.

Side by side

gpt-oss-20bQwen2.5-Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index32.540.7
Released2025-08-052025-01-25
WeightsOpenProprietary
Context window131K—
Max output16K—
Input $ / M tokens$0.018—
Output $ / M tokens$0.09—
Results tracked3427

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

Category by category

Coding Qwen2.5-Max leads

gpt-oss-20b: 37.6 (#192), Qwen2.5-Max: 41.8 (#117)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Coding13061359
SciCode34.4%—
WeirdML40.9%—
LiveBench Coding—64.4%
ALE-Bench566.05—

Agentic & Tool Use Not comparable

gpt-oss-20b: 9.3 (#154), Qwen2.5-Max: —

Benchmarkgpt-oss-20bQwen2.5-Max
Terminal-Bench3.4%—

Reasoning Qwen2.5-Max leads

gpt-oss-20b: 19.3 (#261), Qwen2.5-Max: 25.6 (#147)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Hard Prompts12741360
Epoch Capabilities Index137.82132.53
Kagi LLM Benchmark53.2%—
CritPt1.4%—
Chess Puzzles4%—
LiveBench Reasoning—51.4%
DTBench68%—
LiveBench Data Analysis—67.9%
LMCA14.5%—
LiveBench—62.3%

Math gpt-oss-20b leads

gpt-oss-20b: 39.4 (#103), Qwen2.5-Max: 36.9 (#162)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Math13171369
OTIS Mock AIME 2024-202565.3%—
Omni-MATH56.5%—
LiveBench Math—58.4%

Knowledge Too close to call

gpt-oss-20b: 34.6 (#195), Qwen2.5-Max: 35.3 (#186)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Expert12581337
GPQA Diamond60.8%—
MMLU-Pro74%—
Confabulations—21.8%
GPQA (HELM)59.4%—

Multilingual Qwen2.5-Max leads

gpt-oss-20b: 42.2 (#197), Qwen2.5-Max: 48.1 (#146)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Non-English12681352
LMArena Chinese13141382
LMArena German12551350
LMArena Japanese12441300
LMArena Korean12361304
LMArena Russian12781353
LMArena Spanish12671377
LMArena French—1396

Instruction Following Qwen2.5-Max leads

gpt-oss-20b: 61.8 (#240), Qwen2.5-Max: 71.3 (#152)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Instruction Following12361335
LiveBench Instruction Following—75.3%
IFEval73.2%—

Long Context Qwen2.5-Max leads

gpt-oss-20b: 37.9 (#209), Qwen2.5-Max: 41.4 (#142)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Longer Query12501358

Writing & Preference Qwen2.5-Max leads

gpt-oss-20b: 35.5 (#265), Qwen2.5-Max: 55.4 (#146)

Benchmarkgpt-oss-20bQwen2.5-Max
LMArena Text12871367
LMArena Creative Writing12011339
LMArena Multi-Turn12681364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing666—
WildBench73.7%—
LiveBench Language—56.3%

Frequently asked questions

Is gpt-oss-20b better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 32.5 on the Noometry Index.

Is gpt-oss-20b or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 37.6 in the Noometry coding category.

How many benchmarks do gpt-oss-20b and Qwen2.5-Max share?

17 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper