Noometry

Model comparison

GLM-4.5 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GLM-4.5 scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 28.6.
  • GLM-4.5 is cheaper at $0.60 / $2.20 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 has downloadable open weights; the other is API-only.

Side by side

GLM-4.5Step 5 Preview
ProviderZ.ai (Zhipu)StepFun
Noometry Index42.047.9
Released2025-07-272026-09-16
WeightsOpenProprietary
Context window131K1.02M
Max output98K66K
Input $ / M tokens$0.60$1
Output $ / M tokens$2.20$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: 41.4 (#125), Step 5 Preview: 51.8 (#36)

BenchmarkGLM-4.5Step 5 Preview
LMArena Coding14341480
SWE-bench Verified (bash only)54.2%—
LMArena WebDev—1564
SciCode—58.9%
WeirdML40.6%—
ALE-Bench344.82—
AlgoTune1.52—

Reasoning Step 5 Preview leads

GLM-4.5: 28.6 (#100), Step 5 Preview: 40.0 (#57)

BenchmarkGLM-4.5Step 5 Preview
LMArena Hard Prompts14291465
Kagi LLM Benchmark57.9%—
CritPt—20.9%

Math Step 5 Preview leads

GLM-4.5: 39.0 (#116), Step 5 Preview: 46.1 (#72)

BenchmarkGLM-4.5Step 5 Preview
LMArena Math14271470
ProofBench—42%

Knowledge Step 5 Preview leads

GLM-4.5: 35.9 (#179), Step 5 Preview: 41.2 (#112)

BenchmarkGLM-4.5Step 5 Preview
LMArena Expert14331470
Humanity's Last Exam8.3%—
Confabulations11.3%—

Multimodal Not comparable

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

BenchmarkGLM-4.5Step 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

GLM-4.5: 52.8 (#77), Step 5 Preview: 53.8 (#54)

BenchmarkGLM-4.5Step 5 Preview
LMArena Non-English14171432
LMArena Chinese14651519
LMArena Russian14141436
LMArena Spanish14541439
LMArena French1418—
LMArena German1407—
LMArena Japanese1415—
LMArena Korean1380—

Instruction Following Step 5 Preview leads

GLM-4.5: 74.1 (#104), Step 5 Preview: 76.0 (#50)

BenchmarkGLM-4.5Step 5 Preview
LMArena Instruction Following14041444

Long Context Step 5 Preview leads

GLM-4.5: 38.2 (#201), Step 5 Preview: 44.5 (#64)

BenchmarkGLM-4.5Step 5 Preview
LMArena Longer Query14121455
Fiction.LiveBench58.3%—

Writing & Preference Step 5 Preview leads

GLM-4.5: 57.5 (#127), Step 5 Preview: 62.8 (#71)

BenchmarkGLM-4.5Step 5 Preview
LMArena Text14301442
LMArena Creative Writing13951410
LMArena Multi-Turn14151447
Short-Story Creative Writing73.4%—
EQ-Bench Creative Writing1343—

Frequently asked questions

Is GLM-4.5 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.0 on the Noometry Index.

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

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Step 5 Preview lists at $1 and $2.70.

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

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 41.4 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 and Step 5 Preview share?

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

Related comparisons

Go deeper