GitHub[208K]试用 OpenCode

CompareAI models

  1. DeepSeek V4.1 FlashDeepSeek
  2. Gemini 3.8 FlashGoogle
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4.1 Flash100/100100/10060/10080/10033/10092/100
Gemini 3.8 Flash50/10088/10039/10092/10083/10050/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image
Text, Image, Video, Audio, Pdf
Output modalities
Text
Text
Providers
Pricing
Input
$0.30/ 1M
$0.75/ 1M
Output
$1.20/ 1M
$3.75/ 1M
Cached input
$0.006/ 1M
$0.07/ 1M
MomentumLast 2 mo
Unique users
1.2M
0
Completed sessions
20,579,561
16
Token share
15.3%
0%
Tokens
137T+100%
00%
AUG 7OCT 1
No trend data
RetentionWeek 1
Returning users
58.4%102K user-weeks
Pending

Related comparisons. Other model pairs to check.