gpt-6IMAGE
Astra 在 ARC-AGI-3 上 99.9% 与 62.7% 之争
同一模型同一测试，因外围脚手架不同得出 99.9% 和 62.7% 两个分数，ARC Prize 称这不代表 AGI。
TNW
@thenextweb2026.09.14收录原推发布于 2026.09.08
TNW @thenextweb原推发布于 2026.09.08
OpenAI published 99.9%. The benchmark's own software returned 62.7%. Same model, same test, different scaffolding around it. ARC Prize printed both numbers and says it is not claiming AGI. https://thenextweb.com/news/openai-astra-arc-agi-3-harness-62-7-vs-99-9-benchmark-revisions
x.com/thenextweb/status/2097074513485680716采集于 2026.09.14 15:56