精选理由
OpenAI的Astra在ARC-AGI-3上达到99%分，96%关卡超越人类，表现惊艳。
OpenAI的GPT-6 Astra模型在ARC-AGI-3基准上得分达到63%。通过新的provider adapter harness，该模型得分提升至99%。Astra在ARC-AGI-3的96%关卡上超越了人类表现。该模型构建了我们见过的最精确的新环境符号模型。
原文 · Greg Brockman
arc-agi-3 is now saturated
arc-agi-3 is now saturated ARC Prize @arcprize GPT-6 Astra by @OpenAI achieves SOTA on ARC-AGI: - Astra scores 63% on ARC-AGI-3, 99% via a new provider adapter harness - It surpasses human performance on 96% of ARC-AGI-3 levels - It builds the most precise symbolic model of novel environments we've seen Our analysis: 🔗 View Quoted Tweet 💬 73 🔄 76 ❤️ 1493 👀 96743 📊 150 ⚡