GitHub[220K]Try OpenCode

Compare AI models: Claude Haiku 5.5 vs DeepSeek V4 Flash

  1. Claude Haiku 5.5Anthropic
  2. DeepSeek V4 FlashDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Claude Haiku 5.569/10025/10071/10081/10050/10050/100
DeepSeek V4 Flash26/10073/10053/10081/1000/1000/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.10/ 1M
$0.44/ 1M
Output
$0.50/ 1M
$1.32/ 1M
Cached input
$0.01/ 1M
$0.01/ 1M
MomentumLast 2 mo
Unique users
121K
1.7M
Completed sessions
1,277,869
25,275,722
Token share
0.08%
6.74%
Tokens
1T+100%
81T-71%
SEP 3OCT 28
SEP 3OCT 28
RetentionWeek 1
Returning users
59.6%3.2K user-weeks
63.1%139K user-weeks

Related comparisons. Other model pairs to check.