GPT-6 Luna (Non-reasoning) vs Llama 3 Instruct 8B

GPT-6 Luna (Non-reasoning) vs Llama 3 Instruct 8B. A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

OpenAIGPT-6 Luna (Non-reasoning)Off the frontier
Intelligence
18.50
Total cost
$19.2
MetaLlama 3 Instruct 8BNot ranked · benchmark data missing
Intelligence
4.80
Total cost
-
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.

MetricGPT-6 Luna (Non-reasoning)Llama 3 Instruct 8BDifference
Intelligence (higher is better)18.54.8−74.1% Llama 3 Instruct 8B is 74.1% less intelligent
Total AA cost (lower is better)$19.16Not reported— not comparable
End-to-end time (lower is better)5.09sNot reported— not comparable
Price per 1M tokens (in / out)$0.10 / $0.50$0.04 / $0.14
Input modalitiesText, ImageText
Open this matchup in the interactive pickerGPT-6 Luna (Non-reasoning): what beats itLlama 3 Instruct 8B: what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-6-luna-non-reasoning/llama-3-instruct-8b · Markdown: /api/v1/compare/gpt-6-luna-non-reasoning/llama-3-instruct-8b?format=md · llms.txt · agent skill