Noometry

Model comparison

GLM-4.6 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 43.8 to 40.9 on the Noometry Index.

Last verified . 3 shared benchmarks.

GLM-4.6 Z.ai (Zhipu)

40.9

Rank #132 Confirmed

Step 5 Preview StepFun

43.8

Rank #78 Reported

Summary

  • They share 3 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 23.1.
  • The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 58.9% for Step 5 Preview.
  • GLM-4.6 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 205K.
  • GLM-4.6 has downloadable open weights; the other is API-only.

Side by side

GLM-4.6Step 5 Preview
ProviderZ.ai (Zhipu)StepFun
Noometry Index40.943.8
Released2025-09-302026-09-16
WeightsOpenProprietary
Context window205K1.02M
Max output131K66K
Input $ / M tokens$0.60$1
Output $ / M tokens$2.20$2.70
Results tracked293

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

Category by category

Coding Step 5 Preview leads

GLM-4.6: 39.9 (#137), Step 5 Preview: 50.6 (#40)

BenchmarkGLM-4.6Step 5 Preview
LMArena WebDev13391569
SciCode38.4%58.9%
SWE-bench Verified (bash only)55.4%—
LMArena Coding1449—
ALE-Bench340.82—

Agentic & Tool Use Not comparable

GLM-4.6: 32.1 (#60), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
Terminal-Bench24.5%—
Berkeley Function Calling Leaderboard72.4%—

Reasoning Step 5 Preview leads

GLM-4.6: 23.1 (#168), Step 5 Preview: 38.0 (#58)

BenchmarkGLM-4.6Step 5 Preview
CritPt1.1%20.9%
Kagi LLM Benchmark47.4%—
LMArena Hard Prompts1440—

Math Not comparable

GLM-4.6: 36.4 (#115), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
LMArena Math1431—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Not comparable

GLM-4.6: 39.6 (#118), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
Vectara Hallucination Rate9.5%—
LMArena Expert1432—

Multilingual Not comparable

GLM-4.6: 53.6 (#62), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
LMArena Non-English1426—
LMArena Chinese1500—
LMArena French1459—
LMArena German1447—
LMArena Japanese1394—
LMArena Korean1401—
LMArena Russian1418—
LMArena Spanish1436—

Instruction Following Not comparable

GLM-4.6: 74.5 (#93), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
LMArena Instruction Following1410—

Long Context Not comparable

GLM-4.6: 43.4 (#91), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
LMArena Longer Query1423—

Writing & Preference Not comparable

GLM-4.6: 61.3 (#86), Step 5 Preview: —

BenchmarkGLM-4.6Step 5 Preview
LMArena Text1440—
LMArena Creative Writing1411—
EQ-Bench Creative Writing1411—
LMArena Multi-Turn1427—

Frequently asked questions

Is GLM-4.6 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 40.9 on the Noometry Index.

Which is cheaper, GLM-4.6 or Step 5 Preview?

GLM-4.6 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-4.6 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 39.9 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 205K.

How many benchmarks do GLM-4.6 and Step 5 Preview share?

3 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper