OpenAI Luna Maintains High ARC-AGI Score After 80% Price Cut
Following an 80% price reduction, OpenAI's GPT-5.6 Luna model was retested by the ARC Prize team and maintained strong performance, scoring 90.7% on the ARC-AGI-1 benchmark. The results dismiss rumors of degraded capabilities, proving the model remains highly capable despite significantly lower costs.
2026-08-07 ~ 2026-08-08 · 3 related posts
- Episode 1: OpenAI Cuts Model Price by 80% via Kernel Optimization(2026-08-07, 2 posts)
- Episode 2: OpenAI Luna Maintains High ARC-AGI Score After 80% Price Cut(2026-08-07, 3 posts)
- OpenAI Luna Maintains Performance on ARC-AGI After 80% Price Cut — GregKamradt · 2026-08-07
- OpenAI's Luna Aces ARC-AGI-1 at 90.7% with Massive 80% Cost Reduction — burny_tech · 2026-08-07
- OpenAI's GPT-5.6 Luna Retests on ARC-AGI After 80% Price Cut — GregKamradt · 2026-08-08