ARC Prize· @arcprize · X·· 2 小时前AI 评分53
AI 导读
ARC Prize 解释在 ARC-AGI-2 榜单中省略 Claude Haiku 5.5 的 max reasoning 结果，因为该设置只完成 120 个任务中的 74 个，且许多未完成的尝试在耗尽输出预算前无法返回可解析的答案。完整结果见 https://arcprize.org/results/anthropic-claude-haiku-5-5。
正文
@AnthropicAI On ARC-AGI-2, we omitted max reasoning because it completed only 74 of 120 tasks, with many incomplete attempts failing to return parseable answers before exhausting the output budget.
Full results: https://arcprize.org/results/anthropic-claude-haiku-5-5
来源：ARC Prize · x.com