GitHub[208K]試用 OpenCode

CompareAI models

  1. DeepSeek V4 FlashDeepSeek
  2. Muse Spark 1.3Meta
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash100/10074/10072/10081/1000/100No data
Muse Spark 1.3100/100No data34/10093/10083/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text
Text, Image, Video, Pdf, Audio
Output modalities
Text
Text
Providers
Pricing
Input
$0.15/ 1M
$1.25/ 1M
Output
$0.60/ 1M
$4.25/ 1M
Cached input
$0.003/ 1M
$0.15/ 1M
MomentumLast 2 mo
Unique users
4.4M
0
Completed sessions
34,032,117
23
Token share
44.7%
0%
Tokens
298T+139%
00%
JUL 25SEP 18
No trend data
RetentionWeek 1
Returning users
68.3%483K user-weeks
Pending

Related comparisons. Other model pairs to check.