GitHub[208K]試用 OpenCode

CompareAI models

  1. DeepSeek V4 Flash Vision ExpDeepSeek
  2. MiMo-V2.5Xiaomi
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash Vision Exp100/100No data72/10081/10033/100No data
MiMo-V2.5100/100No data53/10093/10067/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image
Text, Image, Audio, Video
Output modalities
Text
Text
Providers
Pricing
Input
$0.15/ 1M
$0.40/ 1M
Output
$0.60/ 1M
$2.00/ 1M
Cached input
$0.003/ 1M
$0.08/ 1M
MomentumLast 2 mo
Unique users
268K
1.9M
Completed sessions
609,758
49,736,350
Token share
1.01%
8.5%
Tokens
6.7T+100%
57T+352%
JUL 25SEP 18
JUL 25SEP 18
RetentionWeek 1
Returning users
69.6%14K user-weeks
72.9%26K user-weeks

Related comparisons. Other model pairs to check.