GitHub[220K]Try OpenCode

Compare AI models: DeepSeek V4 Flash vs MiMo-V2.5

  1. DeepSeek V4 FlashDeepSeek
  2. MiMo-V2.5Xiaomi
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash26/10073/10074/10081/1000/1000/100
MiMo-V2.517/10053/10074/10092/10067/10050/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text
Text, Image, Audio, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.14/ 1M
$0.14/ 1M
Output
$0.28/ 1M
$0.28/ 1M
Cached input
$0.0028/ 1M
$0.0028/ 1M
MomentumLast 2 mo
Unique users
1.8M
1M
Completed sessions
26,060,217
42,018,028
Token share
7.14%
2.39%
Tokens
85T-69%
29T-23%
SEP 2OCT 27
SEP 2OCT 27
RetentionWeek 1
Returning users
63.1%139K user-weeks
66.9%18K user-weeks

Related comparisons. Other model pairs to check.