Model Releases
GPT-5.5 on ARC-AGI (Verified) ARC-AGI-2: - Max: 85.0%, 1.87 - High: 83.3%, 1.45 - Med: 70.4%, 0.86 - Low: 33%, 0.35 GPT-5.5 is now state…
GPT-5.5 achieved state-of-the-art performance on the ARC-AGI-2 benchmark, with scores ranging from 85.0% on maximum difficulty tasks to 33% on low difficulty tasks. The model demonstrated consistent i
GPT-5.5 achieved state-of-the-art performance on the ARC-AGI-2 benchmark, with scores ranging from 85.0% on maximum difficulty tasks to 33% on low difficulty tasks. The model demonstrated consistent improvement across difficulty tiers (Max: 1.87, High: 1.45, Med: 0.86, Low: 0.35 score metrics), establishing it as a new performance leader on this abstract reasoning and general intelligence evaluation.
Source: Francois Chollet (X) | 2026-04-23