GitHub[208K]Try OpenCode

CompareAI models

  1. Qwen3.8 FlashAlibabaHollow points use fallbacks · hover for details
  2. Muse Spark 1.3 ContributorMeta
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
Muse Spark 1.3 Contributor100/100100/10085/10092/10083/100100/100
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text, Image, Video
Text, Image, Video, Pdf, Audio
Output modalities
Text
Text
Providers
Pricing
Input
$0.15/ 1M
$0.10/ 1M
Output
$0.47/ 1M
$0.20/ 1M
Cached input
$0.02/ 1M
$0.002/ 1M
MomentumLast 2 mo
Unique users
125K
735K
Completed sessions
861,361
203,223,650
Token share
0.22%
14.4%
Tokens
1.7T+100%
111T+100%
JUL 31SEP 24
JUL 31SEP 24
RetentionWeek 1
Returning users
70.9%3.7K user-weeks
83.3%13K user-weeks

Related comparisons. Other model pairs to check.