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 5.569/10025/10072/10081/10050/10050/100
DeepSeek V4 Flash26/10073/10065/10081/1000/1000/100
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
$0.22/ 1M
Output
$0.50/ 1M
$0.66/ 1M
Cached input
$0.01/ 1M
$0.007/ 1M
MomentumLast 2 mo
Unique users
134K
1.5M
Completed sessions
1,389,350
22,561,724
Token share
0.09%
6.03%
Tokens
1.1T+100%
74T-74%
SEP 5OCT 30
SEP 5OCT 30
RetentionWeek 1
Returning users
59.6%3.2K user-weeks
63.1%139K user-weeks

Related comparisons. Other model pairs to check.