GitHub[208K]Try OpenCode

Compare AI models: GPT-6 Luna vs Sonar Pro

  1. GPT-6 LunaOpenAIHollow points use fallbacks · hover for details
  2. Sonar ProPerplexityHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
GPT-6 Luna50/100 — Reasoning supported; no comparable benchmark47/10073/10098/10050/10050/100 — Tool calling supported; no comparable benchmark
Sonar Pro0/100 — Reasoning not supported6/1009/10046/10033/1000/100 — Tool calling not supported
Overview
Author
Context length
1.1M
200K
Reasoning
True
False
Input modalities
Text, Image, Pdf
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.10/ 1M
$3.90/ 1M
Output
$0.50/ 1M
$20/ 1M
Cached input
$0.01/ 1M
Unknown
MomentumLast 2 mo
Unique users
401K
No usage
Completed sessions
2,867,803
No usage
Token share
0.23%
No usage
Tokens
2.3T+100%
No usage
AUG 23OCT 17
No trend data
RetentionWeek 1
Returning users
65.2%3.5K user-weeks
Pending

Related comparisons. Other model pairs to check.