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 placeholder38/10081/10050/10050/100 — Tool calling supported; no comparable benchmark
GLM-5.2100/100100/10031/10081/1000/10088/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$1.00/ 1M
$1.20/ 1M
Output
$2.70/ 1M
$4.18/ 1M
Cached input
$0.05/ 1M
$0.30/ 1M
MomentumLast 2 mo
Unique users
117K
157K
Completed sessions
2,645,357
661,367
Token share
0.6%
0.06%
Tokens
7.2T+100%
714B-87%
SEP 2OCT 27
SEP 2OCT 27
RetentionWeek 1
Returning users
58.8%2.1K user-weeks
52.3%13K user-weeks

Related comparisons. Other model pairs to check.