R

REBench

Tool / Product

A benchmark suite consisting of small, atomic software tasks used by meters to evaluate model behavior.

Mentioned in 1 video

Measuring Exponential Trends Rising (in AI) — Joel Becker, METR

Measuring Exponential Trends Rising (in AI) — Joel Becker, METR

Latent Space

A benchmark suite consisting of small, atomic software tasks used by meters to evaluate model behavior.