GitHub[195K]Try OpenCode

CompareAI models

  1. Qwen3.8 Max 0902Alibaba
  2. Kimi K2.5Moonshot
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.8 Max 0902100/100No data30/10081/10067/100No data
Kimi K2.5100/10020/10045/10063/10050/100No data
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text, Image, Video, Pdf
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$0.60/ 1M
Output
$6.00/ 1M
$3.00/ 1M
Cached input
$0.25/ 1M
$0.10/ 1M
MomentumLast 2 mo
Unique users
No usage
58K
Completed sessions
No usage
3,159
Token share
No usage
0.01%
Tokens
No usage
39B-85%
No trend data
JUL 12SEP 5
RetentionWeek 1
Returning users
Pending
72.1%875 user-weeks

Related comparisons. Other model pairs to check.