GitHub[195K]ลองใช้ OpenCode

CompareAI models

  1. Claude Sonnet 4.5 (latest)Anthropic
  2. DeepSeek V4 FlashDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Claude Sonnet 4.5 (latest)100/10033/10012/10043/10050/100No data
DeepSeek V4 Flash100/10074/10081/10082/1000/100No data
Overview
Author
Context length
200K
1M
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$3.00/ 1M
$0.14/ 1M
Output
$15/ 1M
$0.28/ 1M
Cached input
$0.30/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
0
3.7M
Completed sessions
0
19,449,949
Token share
0%
59.2%
Tokens
00%
263T+86%
No trend data
JUL 5AUG 29
RetentionWeek 1
Returning users
Pending
68.7%354K user-weeks

Related comparisons. Other model pairs to check.