GitHub[150K]Try OpenCode

CompareAI models

  1. Step 3.7 FlashStepFun
  2. GLM-5.1Zhipu
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Step 3.7 Flash37/10096/10069/10050/10060/10056/100
GLM-5.1100/10085/10038/10038/1000/10056/100
Overview
Author
Context length
256K
200K
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.20/ 1M
$1.40/ 1M
Output
$1.15/ 1M
$4.40/ 1M
Cached input
$0.04/ 1M
$0.26/ 1M
MomentumLast 2 mo
Unique users
No usage
232K
Completed sessions
No usage
557,515
Token share
No usage
1.19%
Tokens
No usage
1.6T-16%
No trend data
MAY 20JUL 14

Related comparisons. Other model pairs to check.