Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Why this source is here

A large collaborative benchmark explicitly concerned with extrapolating capability.

Verification

Content-verified on 2026-07-27: the canonical source and its title were resolved during the Atlas review. This is not an endorsement of the source’s argument.

Authors

Srivastava et al.

Identifier

arXiv:2206.04615