Apertus 70B Instruct vs GPT-5.6 Luna (Non-reasoning)

Apertus 70B Instruct vs GPT-5.6 Luna (Non-reasoning). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

Swiss AI InitiativeApertus 70B InstructNot ranked · benchmark data missing
Intelligence
5.10
Total cost
-
OpenAIGPT-5.6 Luna (Non-reasoning)Off the frontier
Intelligence
15.50
Total cost
$23.0
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.

MetricApertus 70B InstructGPT-5.6 Luna (Non-reasoning)Difference
Intelligence (higher is better)5.115.5+203.9% GPT-5.6 Luna (Non-rea… is 3.0× more intelligent
Total AA cost (lower is better)Not reported$22.97— not comparable
End-to-end time (lower is better)Not reported4.98s— not comparable
Price per 1M tokens (in / out)—$0.20 / $1.20
Input modalitiesTextText, Image
Open this matchup in the interactive pickerApertus 70B Instruct: what beats itGPT-5.6 Luna (Non-reasoning): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/apertus-70b-instruct/gpt-5-6-luna-non-reasoning · Markdown: /api/v1/compare/apertus-70b-instruct/gpt-5-6-luna-non-reasoning?format=md · llms.txt · agent skill