GitHub[195K]Try OpenCode

CompareAI models

  1. Qwen3.8 Max 0902Alibaba
  2. DeepSeek V4 FlashDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.8 Max 0902100/100No data30/10081/10067/100No data
DeepSeek V4 Flash100/10074/10060/10081/1000/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$0.44/ 1M
Output
$6.00/ 1M
$1.32/ 1M
Cached input
$0.25/ 1M
$0.01/ 1M
MomentumLast 2 mo
Unique users
No usage
4.1M
Completed sessions
No usage
23,821,800
Token share
No usage
56.9%
Tokens
No usage
280T+103%
No trend data
JUL 12SEP 5
RetentionWeek 1
Returning users
Pending
69.2%419K user-weeks

Related comparisons. Other model pairs to check.