GitHub[195K]Try OpenCode

CompareAI models

  1. Qwen3.8 MaxAlibaba
  2. Gemini 2.5 Computer Use PreviewGoogle
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.8 Max100/100No data31/10081/10067/100No data
Gemini 2.5 Computer Use Preview100/100No data24/10018/10033/100No data
Overview
Author
Context length
1M
128K
Reasoning
True
True
Input modalities
Text, Image, Video, Pdf
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$2.00/ 1M
$1.25/ 1M
Output
$6.00/ 1M
$10/ 1M
Cached input
$0.25/ 1M
Unknown
MomentumLast 2 mo
Unique users
49K
No usage
Completed sessions
38,204
No usage
Token share
0.04%
No usage
Tokens
101B+100%
No usage
JUN 20AUG 14
No trend data

Related comparisons. Other model pairs to check.