GitHub[195K]Try OpenCode

CompareAI models

  1. GPT-5.6 LunaOpenAI
  2. Step 3.5 Flash 2603StepFun
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
GPT-5.6 Luna39/10081/10065/10099/10050/10069/100
Step 3.5 Flash 2603100/10092/10083/10054/1000/10090/100
Overview
Author
Context length
1.1M
256K
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.20/ 1M
$0.10/ 1M
Output
$1.20/ 1M
$0.30/ 1M
Cached input
$0.02/ 1M
$0.02/ 1M
MomentumLast 2 mo
Unique users
403K
No usage
Completed sessions
754,207
No usage
Token share
1.22%
No usage
Tokens
5.3T+100%
No usage
JUL 4AUG 28
No trend data
RetentionWeek 1
Returning users
49.8%18K user-weeks
Pending

Related comparisons. Other model pairs to check.