GitHub[208K]試用 OpenCode

CompareAI models

  1. Jamba LargeAi21
  2. MiMo-V2.5Xiaomi
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Jamba Large0/100No data25/10052/1000/100No data
MiMo-V2.5100/100No data53/10093/10067/100No data
Overview
Author
Context length
256K
1M
Reasoning
False
True
Input modalities
Text
Text, Image, Audio, Video
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$0.40/ 1M
Output
$8.00/ 1M
$2.00/ 1M
Cached input
Unknown
$0.08/ 1M
MomentumLast 2 mo
Unique users
No usage
1.9M
Completed sessions
No usage
49,736,350
Token share
No usage
8.5%
Tokens
No usage
57T+352%
No trend data
JUL 25SEP 18
RetentionWeek 1
Returning users
Pending
72.9%26K user-weeks

Related comparisons. Other model pairs to check.