How enabling two settings tripled our scores on the ARC-AGI-3 benchmark
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
Enabling retained reasoning and compaction tripled GPT-5.6 scores on ARC-AGI-3 while improving efficiency. For production agents, this means API configuration can materially change benchmark and task performance without a model swap, so long-running reasoning workloads should preserve intermediate reasoning state and compact context instead of repeatedly restarting or truncating it.
Enabling two specific API settings resulted in a threefold increase in GPT-5.6's scores on the ARC-AGI-3 benchmark; this significant performance boost will likely impact the optimization strategies for LLMs and agents in production, as it demonstrates that tweaking API settings can substantially improve model efficiency and accuracy.