How enabling two settings tripled our scores on the ARC-AGI-3 benchmark
Mirrored from OpenAI for archival readability. Support the source by reading on the original site.
How two API settings improved GPT-5.6 performance on ARC-AGI-3, boosting scores and efficiency by retaining reasoning and enabling compaction.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.