GitHub[208K]Try OpenCode

CompareAI models

  1. Qwen3.8 FlashAlibabaHollow points use fallbacks · hover for details
  2. GLM-5.3Zhipu
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Qwen3.8 Flash50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder73/10080/10050/10050/100 — Tool calling supported; no comparable benchmark
GLM-5.385/100100/10034/10080/1000/100100/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.15/ 1M
$1.40/ 1M
Output
$0.47/ 1M
$4.40/ 1M
Cached input
$0.02/ 1M
$0.26/ 1M
MomentumLast 2 mo
Unique users
137K
309K
Completed sessions
968,640
549,172
Token share
0.22%
0.16%
Tokens
1.9T+100%
1.4T+100%
AUG 4SEP 28
AUG 4SEP 28
RetentionWeek 1
Returning users
60%5.5K user-weeks
53.6%21K user-weeks

Related comparisons. Other model pairs to check.