GitHub[208K]Try OpenCode

CompareAI models

  1. GPT-5.6 LunaOpenAI
  2. Grok 4.6xAIHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
GPT-5.6 Luna67/10081/10063/10098/10050/10064/100
Grok 4.650/100 — Reasoning supported; no comparable benchmark38/10030/10072/10033/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1.1M
500K
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.20/ 1M
$2.00/ 1M
Output
$1.20/ 1M
$6.00/ 1M
Cached input
$0.02/ 1M
$0.50/ 1M
MomentumLast 2 mo
Unique users
647K
48K
Completed sessions
2,104,007
100,086
Token share
0.91%
0.01%
Tokens
7.3T+3,735%
71B+100%
AUG 2SEP 26
AUG 2SEP 26
RetentionWeek 1
Returning users
58.8%45K user-weeks
51.8%1.8K user-weeks

Related comparisons. Other model pairs to check.