Primary sourcerohanpaul_ai
View sourceEvent ·Multi-source
Stanford 论文提出 Joules-to-GDP:衡量每焦耳算力产出的经济价值
Stanford 研究人员构建了 Joules-to-GDP 指标,计算 AI 每消耗一焦耳能量所产出的净美元价值。他们在 GDPval 的 220 个专业任务(覆盖 44 个职业)上测试了 5 个开源模型。结果显示 GLM 5.2 单任务净价值最高,但 Gemma 4 31B 用 23% 的能量达到了它 56% 的价值。Qwen3.6-27B 从 1 张 H100 扩到 8 张,任务时间只缩短 22%,能耗却是 3.2 倍。GPT-OSS 120B 在价格和速度接近的情况下,能耗比 GLM 5.2 低 68%。
Current read
Stanford 搞了个新指标算 AI 每焦耳能赚多少钱,结果小模型反而更划算,8 张 H100 只比 1 张快 22%,选模型前值得看看这套思路。
8 sources54° AI heatLast updated 2026/11/4 21:29:20
Evidence
8 sourcesRelated source 1Stanford AI Lab
View sourceRelated source 2arXiv cs.LG
View sourceRelated source 3Jerry Liu
View sourceRelated source 4Gorden Sun
View sourceRelated source 5marktechpost
View sourceRelated source 6AIGCLINK
View sourceRelated source 7vLLM
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.