Noometry

Model comparison

GLM-4.5-Air vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 38.9 on the Noometry Index. GLM-4.5-Air costs 3.4× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 13 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Step 5 Preview leads 51.8 to 33.3.
  • GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 131K.
  • GLM-4.5-Air has downloadable open weights; the other is API-only.

Side by side

GLM-4.5-AirStep 5 Preview
ProviderZ.ai (Zhipu)StepFun
Noometry Index38.947.9
Released2025-07-202026-09-16
WeightsOpenProprietary
Context window131K1.02M
Max output98K66K
Input $ / M tokens$0.20$1
Output $ / M tokens$1.10$2.70
Results tracked2718

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

Category by category

Coding Step 5 Preview leads

GLM-4.5-Air: 33.3 (#259), Step 5 Preview: 51.8 (#36)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Coding13971480
LMArena WebDev—1564
SciCode—58.9%
GSO2.9%—

Reasoning Step 5 Preview leads

GLM-4.5-Air: 24.1 (#166), Step 5 Preview: 40.0 (#57)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Hard Prompts13791465
Kagi LLM Benchmark43%—
CritPt—20.9%
ForecastBench59.2—

Math Step 5 Preview leads

GLM-4.5-Air: 36.2 (#170), Step 5 Preview: 46.1 (#72)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Math13961470
ProofBench—42%
Omni-MATH39.1%—

Knowledge Step 5 Preview leads

GLM-4.5-Air: 35.0 (#191), Step 5 Preview: 41.2 (#112)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Expert13701470
Humanity's Last Exam8.1%—
MMLU-Pro76.2%—
Vectara Hallucination Rate9.3%—
GPQA (HELM)59.4%—

Multimodal Not comparable

GLM-4.5-Air: —, Step 5 Preview: 41.0 (#41)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

GLM-4.5-Air: 49.1 (#135), Step 5 Preview: 53.8 (#54)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Non-English13661432
LMArena Chinese14261519
LMArena Russian13731436
LMArena Spanish13861439
LMArena French1399—
LMArena German1377—
LMArena Japanese1348—
LMArena Korean1308—

Instruction Following Step 5 Preview leads

GLM-4.5-Air: 69.6 (#171), Step 5 Preview: 76.0 (#50)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Instruction Following13541444
IFEval81.2%—

Long Context Step 5 Preview leads

GLM-4.5-Air: 41.6 (#135), Step 5 Preview: 44.5 (#64)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Longer Query13661455

Writing & Preference Step 5 Preview leads

GLM-4.5-Air: 55.9 (#139), Step 5 Preview: 62.8 (#71)

BenchmarkGLM-4.5-AirStep 5 Preview
LMArena Text13841442
LMArena Creative Writing13431410
LMArena Multi-Turn13711447
WildBench78.9%—

Frequently asked questions

Is GLM-4.5-Air better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 38.9 on the Noometry Index. GLM-4.5-Air costs 3.4× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, GLM-4.5-Air or Step 5 Preview?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is GLM-4.5-Air or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.3 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 131K.

How many benchmarks do GLM-4.5-Air and Step 5 Preview share?

13 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper