GitHub[208K]Try OpenCode

Compare AI models: Claude Haiku 5.5 vs DeepSeek V4 Flash Vision Exp

  1. Claude Haiku 5.5Anthropic
  2. DeepSeek V4 Flash Vision ExpDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Claude Haiku 5.568/10025/10073/10081/10050/10050/100
DeepSeek V4 Flash Vision Exp27/10079/10059/10081/10033/1000/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.10/ 1M
$0.30/ 1M
Output
$0.50/ 1M
$1.20/ 1M
Cached input
$0.01/ 1M
$0.006/ 1M
MomentumLast 2 mo
Unique users
51K
357K
Completed sessions
599,392
1,204,124
Token share
0.04%
0.91%
Tokens
380B+100%
9.3T+2,601%
AUG 23OCT 17
AUG 23OCT 17
RetentionWeek 1
Returning users
Pending
63.1%26K user-weeks

Related comparisons. Other model pairs to check.