Feed Ask Research Search

Feed Ask Research Search

Home Search Ask Research Alerts

GDP X · podgraph

GX

GDP X

Work · mentioned 4 times

AI benchmark built from detailed, realistic real-world tasks.

No connections recorded yet.

Latest news

MTS· 7 Nov
Herbie Bradley says the blog post compares the older GDP Val with GDP X on tasks such as finance, where there are fewer verifiable things, and that GDP X constructed a detailed, realistic set of tasks more representative of the real world.