GitHub[208K]Try OpenCode

Compare AI models: GPT-5.6 Luna vs mai-experimental-test

  1. GPT-5.6 LunaOpenAI
  2. mai-experimental-testHollow 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
mai-experimental-test50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder
Overview
Author
Context length
1.1M
Unknown
Reasoning
True
Unknown
Input modalities
Text, Image, Pdf
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$0.20/ 1M
Unknown
Output
$1.20/ 1M
Unknown
Cached input
$0.02/ 1M
Unknown
MomentumLast 2 mo
Unique users
602K
53K
Completed sessions
2,080,007
544,286
Token share
0.71%
0.02%
Tokens
6.4T+406%
203B+100%
AUG 8OCT 2
AUG 8OCT 2
RetentionWeek 1
Returning users
55%50K user-weeks
Pending

Related comparisons. Other model pairs to check.