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

Practical AI: Tools, Models & Frameworksapibenchmark

What changed

How two API settings improved GPT-5.6 performance on ARC-AGI-3, boosting scores and efficiency by retaining reasoning and enabling compaction.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

  • Measuring progress toward AGI: A cognitive framework
  • Introducing GPT-5.1 for developers
  • How GPT-5.6 fuses frontier intelligence with frontier efficiency

Sources