GPT-5.6 ARC-AGI-3 Score Jumps 3x With Specific API Settings
sandersted · x · 2026-07-30
A tweet discussed GPT-5.6's performance on the ARC-AGI-3 benchmark. While the model performs poorly by default, enabling two specific API settings used internally by ChatGPT and Codex causes its score on the public set to jump 3x, with token efficiency improving by 6x.
This illustrates that actual model performance is highly dependent on product-level engineering and parameter settings, not just the base model.
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