GitHub[195K]Try OpenCode

CompareAI models

  1. Claude Sonnet 5Anthropic
  2. DeepSeek V4 FlashDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Claude Sonnet 5100/10092/10020/10082/10050/10092/100
DeepSeek V4 Flash100/10074/10081/10082/1000/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$0.14/ 1M
Output
$10/ 1M
$0.28/ 1M
Cached input
$0.20/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
No usage
3.7M
Completed sessions
No usage
19,372,562
Token share
No usage
60.1%
Tokens
No usage
262T+86%
No trend data
JUL 4AUG 28
RetentionWeek 1
Returning users
Pending
68.7%354K user-weeks

Related comparisons. Other model pairs to check.