AI News

Claude Fable 5.2 以 75 分登顶 AA-Robotics v0.1,领先 GPT-6…

Artificial Analysis更新于 11月12日 10:33

Claude Fable 5.2 is the new leader on AA-Robotics v0.1, scoring 75, ahead of GPT-6 Astra (69) and GPT-6.1 Sol (65)

AI 导读

Artificial Analysis 的 AA-Robotics v0.1 榜单显示,Claude Fable 5.2 以 75 分成为新榜首,GPT-6 Astra 得 69 分、GPT-6.1 Sol 得 65 分。Fable 5.2 是首个在 measure box 任务上得分的模型,它仅使用视频,把卷尺留作布置,并用卷尺刻度作为比例尺估算箱子尺寸。

推荐理由

AI 评分 55

AA-Robotics v0.1 榜单更新,读者可看到 Claude Fable 5.2 在测量箱体任务上仅凭视频完成估算的具体做法。

主题

标签

正文

Claude Fable 5.2 is the new leader on AA-Robotics v0.1, scoring 75, ahead of GPT-6 Astra (69) and GPT-6.1 Sol (65)

Fable 5.2 is the first model to achieve a score on the measure box task. It did so using purely video, leaving the tape measure as setup and using its markings as a scale to estimate the box size

来源

Artificial Analysis