GitHub[195K]Try OpenCode

CompareAI models

  1. Qwen3.6 PlusAlibaba
  2. DeepSeek V4 ProDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.6 Plus100/100No data46/10081/10050/100No data
DeepSeek V4 Pro100/10087/10036/10081/1000/10044/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.50/ 1M
$1.32/ 1M
Output
$3.00/ 1M
$3.96/ 1M
Cached input
$0.10/ 1M
$0.04/ 1M
MomentumLast 2 mo
Unique users
90K
1.4M
Completed sessions
95,132
2,516,432
Token share
0.04%
4.89%
Tokens
209B-79%
27T+1%
JUL 17SEP 10
JUL 17SEP 10
RetentionWeek 1
Returning users
62.1%3.1K user-weeks
63.9%128K user-weeks

Related comparisons. Other model pairs to check.