Original post · AI translation
@Avanika15 这篇论文真不错
@rohanpaul_ai 谢谢你分享我们的工作，@rohanpaul_ai 🙌🏽🙌🏽🙌🏽
Original
@rohanpaul_ai ty for sharing our work @rohanpaul_ai 🙌🏽🙌🏽🙌🏽
斯坦福大学的一篇新论文发现，较小的 AI 模型每单位能源所创造的经济价值，可能远高于能力最强的模型。
如今世界受到能源和电力的限制，每项 AI 任务消耗多少能源确实应该得到研究。
研究人员在此构建了 Joules-to-GDP，用 AI 完成的工作所创造的美元价值减去其运行成本，再除以消耗的能量（焦耳）来衡量。他们用 GDPval 中涵盖 44 种职业的 220 项专业任务，测试了 5 个开放模型。
> GLM 5.2 每项任务创造的净价值最高，但 Gemma 4 31B 仅用其 23% 的能源，就创造了相当于其 56% 的净价值。
> 将运行 Qwen3.6-27B 的 H100 数量从 1 个增加到 8 个，任务耗时仅缩短了 22%，能源消耗却增至 3.2 倍。
> 尽管 GPT-OSS 120B 与 GLM 5.2 的价格和速度几乎相同，它的能源消耗却低了 68%。
> 用 8 个而不是 1 个 H100 芯片运行同一个模型，任务速度仅提高了 22%，能源消耗却增至 3.24 倍，而完成的工作所创造的美元价值几乎相同。
https://t.co/KAj3vxhHto
Original
New Stanford paper finds that a smaller AI model can return far more economic value per unit of energy than the most capable one. Now that the world is limited by energy/power, how much energy each AI task burns should indeed by studied. Here, the researchers built Joules-to-GDP, which measures the dollar value of an AI's work, minus its running cost, per joule of energy used. They tested 5 open models on 220 professional tasks from GDPval, covering 44 occupations. > GLM 5.2 produced the most net value per task, but Gemma 4 31B got 56% of it with 23% of the energy. > Moving Qwen3.6-27B from 1 to 8 H100s cut task time by just 22% while using 3.2x the energy. > GPT-OSS 120B used 68% less energy than GLM 5.2 despite nearly the same price and speed. > Running the same model on 8 H100 chips instead of 1 made tasks only 22% faster but used 3.24x the energy, for nearly the same dollar value of work https://t.co/KAj3vxhHto