GPT-5.6 ARC-AGI-3 Score Triples When Enabling Thought Memory
sandersted · x · 2026-07-30
An OpenAI researcher shared insights on the synergy between model capabilities and product harnesses. While GPT-5.6 performs poorly by default on the ARC-AGI-3 test, enabling two API settings used in ChatGPT and Codex (allowing the model to remember its thoughts) boosts its score by 3x and improves token efficiency by 6x.
This demonstrates that actual performance is a function of the model combined with its product harness, not just the model alone.
Related event: Optimized Memory Settings Triple GPT-5.6's Score on ARC-AGI-3(27 posts)→
More from Models
- Opus 5.5 still leads a month later, but open-weight decision models are closing in — airesearch12 · 2026-10-16
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16