Model comparison

GLM-4.6 vs Step 3.7 Flash

GLM-4.6 is the stronger model overall, scoring 40.9 to 36.5 on the Noometry Index. Step 3.7 Flash costs 2.4× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Last verified October 10, 2026. 3 shared benchmarks.

GLM-4.6 Z.ai (Zhipu)

40.9

Rank #132 Confirmed

Step 3.7 Flash

StepFun

36.5

Rank #207 Reported

Summary

They share 3 benchmarks with published results for both. GLM-4.6 scores higher in 2 categories and Step 3.7 Flash in 1 category; 2 gaps are clear of the uncertainty.
The widest gap is in math, where Step 3.7 Flash leads 40.9 to 36.4.
Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
Step 3.7 Flash accepts more context: 256K tokens versus 205K.

Side by side

GLM-4.6 and Step 3.7 Flash specifications
	GLM-4.6	Step 3.7 Flash
Provider	Z.ai (Zhipu)	StepFun
Noometry Index	40.9	36.5
Released	2025-09-30	2026-05-29
Weights	Open	Open
Context window	205K	256K
Max output	131K	256K
Input $ / M tokens	$0.60	$0.18
Output $ / M tokens	$2.20	$1.11
Results tracked	29	5

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

Category by category

Coding Too close to call

GLM-4.6: 39.9 (#137), Step 3.7 Flash: 39.4 (#147)

Coding benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
SciCode	38.4%	40%
ALE-Bench	340.82	694.12
SWE-bench Verified (bash only)	55.4%	—
LMArena WebDev	1339	—
LMArena Coding	1449	—

Agentic & Tool Use Not comparable

GLM-4.6: 32.1 (#60), Step 3.7 Flash: —

Agentic & Tool Use benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
Terminal-Bench	24.5%	—
Berkeley Function Calling Leaderboard	72.4%	—

Reasoning GLM-4.6 leads

GLM-4.6: 23.1 (#168), Step 3.7 Flash: 20.9 (#211)

Reasoning benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
CritPt	1.1%	2.3%
Kagi LLM Benchmark	47.4%	—
NYT Connections (extended)	—	39.7%
LMArena Hard Prompts	1440	—

Math Step 3.7 Flash leads

GLM-4.6: 36.4 (#115), Step 3.7 Flash: 40.9 (#74)

Math benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
MathArena Final-Answer Competitions	—	68.5%
LMArena Math	1431	—
FrontierMath (Feb 2025 set)	3.8%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge Not comparable

GLM-4.6: 39.6 (#118), Step 3.7 Flash: —

Knowledge benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
Vectara Hallucination Rate	9.5%	—
LMArena Expert	1432	—

Multilingual Not comparable

GLM-4.6: 53.6 (#62), Step 3.7 Flash: —

Multilingual benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
LMArena Non-English	1426	—
LMArena Chinese	1500	—
LMArena French	1459	—
LMArena German	1447	—
LMArena Japanese	1394	—
LMArena Korean	1401	—
LMArena Russian	1418	—
LMArena Spanish	1436	—

Instruction Following Not comparable

GLM-4.6: 74.5 (#93), Step 3.7 Flash: —

Instruction Following benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
LMArena Instruction Following	1410	—

Long Context Not comparable

GLM-4.6: 43.4 (#91), Step 3.7 Flash: —

Long Context benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
LMArena Longer Query	1423	—

Writing & Preference Not comparable

GLM-4.6: 61.3 (#86), Step 3.7 Flash: —

Writing & Preference benchmarks
Benchmark	GLM-4.6	Step 3.7 Flash
LMArena Text	1440	—
LMArena Creative Writing	1411	—
EQ-Bench Creative Writing	1411	—
LMArena Multi-Turn	1427	—

Frequently asked questions

Is GLM-4.6 better than Step 3.7 Flash?

Which is cheaper, GLM-4.6 or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

Is GLM-4.6 or Step 3.7 Flash better for coding?

They score almost the same on coding (39.9 vs 39.4); test both on your own repository before choosing.

Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 205K.

How many benchmarks do GLM-4.6 and Step 3.7 Flash share?

3 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Step 3.7 Flash has 5.