aiIMAGE
硬核数学科学基准达标成本骤降曲线
Ethan Mollick 分享图表：在多个高难数学与科学基准上拿到 25% 或 75% 分数的成本正快速坍塌，而模型能力同时上升，因此现在只为省钱做优化可能很短视。
Ethan Mollick
@emollick2026.09.24收录原推发布于 2026.09.24
Ethan Mollick @emollick原推发布于 2026.09.24
This is a really important graph showing the cost of achieving 25% or 75% scores in various hard math and science benchmarks. Costs are collapsing even as ability is increasing It is also why optimizing for cost for a particular solution right now may end up being short sighted https://t.co/BQKUyuTHRR
x.com/emollick/status/2102865436459069474采集于 2026.09.24 11:04