GitHub[220K]Try OpenCode

Compare AI models: Step 5 Preview vs GLM-5.2

  1. Step 5 PreviewStepFunHollow points use fallbacks · hover for details
  2. GLM-5.2Zhipu
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Step 5 Preview50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder37/10082/10050/10050/100 — Tool calling supported; no comparable benchmark
GLM-5.2100/100100/10031/10082/1000/10088/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$1.06/ 1M
$1.20/ 1M
Output
$2.86/ 1M
$4.18/ 1M
Cached input
$0.05/ 1M
$0.30/ 1M
MomentumLast 2 mo
Unique users
113K
174K
Completed sessions
2,629,581
655,824
Token share
0.63%
0.07%
Tokens
7.2T+100%
800B-87%
AUG 29OCT 23
AUG 29OCT 23
RetentionWeek 1
Returning users
77.1%933 user-weeks
56.8%16K user-weeks

Related comparisons. Other model pairs to check.