跳到正文
Rohan Paul· @rohanpaul_ai · X·· 2026-07-19AI 评分33
AI 导读

每花费 100 美元,Kimi 完成 14.7 个任务,而 Fable 完成 5.3 个,每美元工作量是后者的 2.8 倍。 在软件工程/DeepSWE 任务上。

正文 · 原文

For every $100 spent, Kimi completes 14.7 tasks versus Fable’s 5.3, giving you 2.8x more work per dollar.

on software engineering/DeepSWE tasks.

引用Zain@ZainHasan6
$4.65/rollout vs $13.41. Per $100 of spend, Kimi solves 14.7 tasks to Fable's 5.3 = 2.8x the work per dollar. A median Kimi rollout takes 66 minutes (Fable: 21). This should improve after the model is released and widely available!
在 X 查看被引用的帖子

来源:Rohan Paul · x.com