How enabling two settings tripled our scores on the ARC-AGI-3 benchmark
OpenAI reports that enabling two API settings significantly improved GPT-5.6's performance on the ARC-AGI-3 benchmark, tripling its scores. The settings, which retain reasoning and enable compaction, also enhanced efficiency.
Why it matters: This shows that adjusting configuration settings can substantially boost AI benchmark performance without major changes to the underlying model.
Full story at: OpenAI News ↗