OpenAI's GPT-6 Astra Hits 99.9% on ARC-AGI-3, Beats Human Action Efficiency

OpenAI's GPT-6 Astra on ARC-AGI-3

ARC Prize reports that OpenAI's GPT-6 Astra achieves state-of-the-art scores on the ARC-AGI-3 benchmark, reaching 99.9% with a provider adapter harness and 62.7% with the standard harness. Notably, Astra used fewer actions than the median human on 96% of levels, surpassing human action efficiency. The model developed compact symbolic world models and custom tools, marking a significant step in agentic AI.