OpenAI's GPT-5.6 Luna Retests on ARC-AGI After 80% Price Cut

GregKamradt · x · 2026-08-08

Following an 80% price reduction for OpenAI's GPT-5.6 Luna model, the ARC Prize Foundation re-evaluated it on the ARC-AGI benchmark.

The results show the model maintained its original performance at a much lower cost: scoring 59.6% on ARC-AGI-2 ($0.18/task) and 90.7% on ARC-AGI-1 ($0.07/task).

Related event: OpenAI Luna Maintains High ARC-AGI Score After 80% Price Cut(3 posts)→

Original post →

More from Models

Models channel →