OpenAI · LIVEBENCH 2026-11-06
gpt-6-luna
Published benchmark results for this specific model configuration.
gpt-6-lunaOverall score63.7 / 100
Cost / successful task$0.125USD · benchmark workload
Weight accessNot reported
Where this configuration performs
Category averages from the same release, on a 0–100 scale.
Task-level results
long agentic24.7reasoning81.8coding70.8browser70.3data analysis73.4research48.5design76.1
Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.