Research · OpenAI Blog ·

How enabling two settings tripled our scores on the ARC-AGI-3 benchmark

How enabling two settings tripled our scores on the ARC-AGI-3 benchmark

OpenAI reports that enabling reasoning retention and compaction in two API settings tripled GPT-5.6’s score on the ARC-AGI-3 benchmark. The settings also improved efficiency by preserving reasoning while reducing context overhead.

Read the full story at OpenAI Blog →