GitHub[208K]Try OpenCode

CompareAI models

  1. Jamba MiniAi21Hollow points use fallbacks · hover for details
  2. Qwen3.8 MaxAlibaba
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Jamba Mini0/100 — Reasoning not supported50/100 — No data; neutral placeholder74/10051/1000/10050/100 — Tool calling supported; no comparable benchmark
Qwen3.8 Max87/100100/10030/10080/10067/10091/100
Overview
Author
Context length
256K
1M
Reasoning
False
True
Input modalities
Text
Text, Image, Video, Pdf
Output modalities
Text
Text
Providers
Pricing
Input
$0.20/ 1M
$2.00/ 1M
Output
$0.40/ 1M
$6.00/ 1M
Cached input
Unknown
$0.25/ 1M
MomentumLast 2 mo
Unique users
No usage
166K
Completed sessions
No usage
388,723
Token share
No usage
0.04%
Tokens
No usage
361B+1,157%
No trend data
AUG 6SEP 30
RetentionWeek 1
Returning users
Pending
42.4%9.1K user-weeks

Related comparisons. Other model pairs to check.