GitHub[220K]Try OpenCode

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

  1. DeepSeek V4 ProDeepSeek
  2. MiMo-V2.5Xiaomi
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/100100/10047/10081/1000/10068/100
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
$0.70/ 1M
$0.14/ 1M
Output
$1.40/ 1M
$0.28/ 1M
Cached input
$0.07/ 1M
$0.0028/ 1M
MomentumLast 2 mo
Unique users
437K
1.1M
Completed sessions
1,422,252
44,075,722
Token share
0.47%
2.56%
Tokens
5.5T-82%
30T-15%
SEP 1OCT 26
SEP 1OCT 26
RetentionWeek 1
Returning users
55%36K user-weeks
66.9%18K user-weeks

Related comparisons. Other model pairs to check.