Claude 4.5 Sonnet (Non-reasoning) vs GPT-6 Luna (Max)

Claude 4.5 Sonnet (Non-reasoning) vs GPT-6 Luna (Max). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

AnthropicClaude 4.5 Sonnet (Non-reasoning)Not ranked · benchmark data missing
Intelligence
19.30
Total cost
-
OpenAIGPT-6 Luna (Max)On the frontier
Intelligence
38.10
Total cost
$122
Verdict

Comparison incomplete

A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

MetricClaude 4.5 Sonnet (Non-reasoning)GPT-6 Luna (Max)Difference
Intelligence (higher is better)19.338.1+97.4% GPT-6 Luna (Max) is 97.4% more intelligent
Total AA cost (lower is better)Not reported$122.05— not comparable
End-to-end time (lower is better)12.54s82.02s+554.1% GPT-6 Luna (Max) is 554.1% slower
Price per 1M tokens (in / out)$3.00 / $15.0$0.10 / $0.50
Input modalitiesText, ImageText, Image
Open this matchup in the interactive pickerClaude 4.5 Sonnet (Non-reasoning): what beats itGPT-6 Luna (Max): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-4-5-sonnet/gpt-6-luna · Markdown: /api/v1/compare/claude-4-5-sonnet/gpt-6-luna?format=md · llms.txt · agent skill