GitHub[195K]Try OpenCode

CompareAI models

  1. Qwen3.8 FlashAlibaba
  2. Llama 4 Maverick 17B InstructMeta
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.8 Flash100/100No data76/10081/10050/100No data
Llama 4 Maverick 17B Instruct0/10013/10068/10081/10033/100No data
Overview
Author
Context length
1M
1M
Reasoning
True
False
Input modalities
Text, Image, Video
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.15/ 1M
$0.27/ 1M
Output
$0.47/ 1M
$0.85/ 1M
Cached input
$0.02/ 1M
Unknown
MomentumLast 2 mo
Unique users
86K
No usage
Completed sessions
409,052
No usage
Token share
0.21%
No usage
Tokens
1.3T+100%
No usage
JUL 22SEP 15
No trend data
RetentionWeek 1
Returning users
72.3%2.2K user-weeks
Pending

Related comparisons. Other model pairs to check.