AI 导读
Claude Fable 5.1 的五档 effort 设置，输出 token 用量跨度达 11 倍，从 low effort 的 13.1M 到 max 的 143.7M，在 Artificial Analysis Intelligence Index 上的得分从 58 到 66。在各 effort 档位上，Fable 5.1 都处于 Intelligence vs Output Tokens 前沿，但其下限高于 GPT-5.6 系列：GPT-5.6 Sol（medium）的 token 用量略低于 Fable 5.1（low），为 12M 对 13.1M。
正文
Claude Fable 5.1's five effort settings span 11x in output token usage, from 13.1M at low effort to 143.7M at max, and score from 58 to 66 on the Artificial Analysis Intelligence Index. Across effort levels Fable 5.1 sits on the Intelligence vs Output Tokens frontier, but its floor is higher than the GPT-5.6 family's: GPT-5.6 Sol (medium) uses marginally fewer tokens than Fable 5.1 (low), 12M against 13.1M.
来源：@ArtificialAnlys · x.com