GitHub[208K]Try OpenCode

CompareAI models

  1. Qwen3.5 PlusAlibaba
  2. DeepSeek V4.1 FlashDeepSeek
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.5 Plus100/100No data49/10081/10033/100No data
DeepSeek V4.1 Flash100/100No data68/10081/10033/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.40/ 1M
$0.21/ 1M
Output
$2.50/ 1M
$0.84/ 1M
Cached input
$0.04/ 1M
$0.0042/ 1M
MomentumLast 2 mo
Unique users
27K
443K
Completed sessions
19,651
7,526,410
Token share
0%
8.44%
Tokens
20B-30%
56T+100%
JUL 25SEP 18
JUL 25SEP 18
RetentionWeek 1
Returning users
69.8%285 user-weeks
Pending

Related comparisons. Other model pairs to check.