Noometry

Model comparison

GLM-4.5-Air vs gpt-oss-20b

GLM-4.5-Air is the stronger model overall, scoring 38.7 to 32.1 on the Noometry Index. gpt-oss-20b costs 12× less per token, which makes it the better buy when GLM-4.5-Air's lead doesn't matter for your workload.

Last verified . 22 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.7

Rank #169 Confirmed

gpt-oss-20b OpenAI

32.1

Rank #249 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-4.5-Air scores higher in 6 categories and gpt-oss-20b in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.5-Air leads 56.1 to 35.8.
  • The biggest single-benchmark swing is Omni-MATH: 39.1% for GLM-4.5-Air and 56.5% for gpt-oss-20b.
  • gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.

Side by side

GLM-4.5-Airgpt-oss-20b
ProviderZ.ai (Zhipu)OpenAI
Noometry Index38.732.1
Released2025-07-202025-08-05
WeightsOpenOpen
Context window131K131K
Max output98K16K
Input $ / M tokens$0.20$0.018
Output $ / M tokens$1.10$0.09
Results tracked2734

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

Category by category

Coding gpt-oss-20b leads

GLM-4.5-Air: 34.5 (#225), gpt-oss-20b: 37.1 (#185)

BenchmarkGLM-4.5-Airgpt-oss-20b
LMArena Coding13971307
SciCode—34.4%
GSO2.9%—
WeirdML—40.9%
ALE-Bench—566.05

Agentic & Tool Use Not comparable

GLM-4.5-Air: —, gpt-oss-20b: 9.2 (#146)

BenchmarkGLM-4.5-Airgpt-oss-20b
Terminal-Bench—3.4%

Reasoning GLM-4.5-Air leads

GLM-4.5-Air: 23.3 (#166), gpt-oss-20b: 18.8 (#251)

BenchmarkGLM-4.5-Airgpt-oss-20b
Kagi LLM Benchmark43%53.2%
LMArena Hard Prompts13791274
CritPt—1.4%
Chess Puzzles—4%
DTBench—68%
LMCA—14.5%
Epoch Capabilities Index—137.81
ForecastBench59.2—

Math gpt-oss-20b leads

GLM-4.5-Air: 33.8 (#166), gpt-oss-20b: 37.6 (#93)

BenchmarkGLM-4.5-Airgpt-oss-20b
Omni-MATH39.1%56.5%
LMArena Math13961317
OTIS Mock AIME 2024-2025—65.3%

Knowledge Too close to call

GLM-4.5-Air: 34.6 (#184), gpt-oss-20b: 34.6 (#186)

BenchmarkGLM-4.5-Airgpt-oss-20b
MMLU-Pro76.2%74%
GPQA (HELM)59.4%59.4%
LMArena Expert13701258
GPQA Diamond—60.8%
Humanity's Last Exam8.1%—
Vectara Hallucination Rate9.3%—

Multilingual GLM-4.5-Air leads

GLM-4.5-Air: 49.4 (#130), gpt-oss-20b: 42.4 (#192)

BenchmarkGLM-4.5-Airgpt-oss-20b
LMArena Non-English13661269
LMArena Chinese14271311
LMArena German13761249
LMArena Japanese13481245
LMArena Korean13061239
LMArena Russian13731279
LMArena Spanish13851267
LMArena French1399—

Instruction Following GLM-4.5-Air leads

GLM-4.5-Air: 69.8 (#165), gpt-oss-20b: 62.0 (#235)

BenchmarkGLM-4.5-Airgpt-oss-20b
IFEval81.2%73.2%
LMArena Instruction Following13531236

Long Context GLM-4.5-Air leads

GLM-4.5-Air: 41.6 (#130), gpt-oss-20b: 37.9 (#203)

BenchmarkGLM-4.5-Airgpt-oss-20b
LMArena Longer Query13671251

Writing & Preference GLM-4.5-Air leads

GLM-4.5-Air: 56.1 (#134), gpt-oss-20b: 35.8 (#260)

BenchmarkGLM-4.5-Airgpt-oss-20b
LMArena Text13841288
LMArena Creative Writing13431201
WildBench78.9%73.7%
LMArena Multi-Turn13711268
EQ-Bench Creative Writing—666

Frequently asked questions

Is GLM-4.5-Air better than gpt-oss-20b?

GLM-4.5-Air is the stronger model overall, scoring 38.7 to 32.1 on the Noometry Index. gpt-oss-20b costs 12× less per token, which makes it the better buy when GLM-4.5-Air's lead doesn't matter for your workload.

Which is cheaper, GLM-4.5-Air or gpt-oss-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.

Is GLM-4.5-Air or gpt-oss-20b better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do GLM-4.5-Air and gpt-oss-20b share?

22 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and gpt-oss-20b has 34.

Related comparisons

Go deeper