Srivastava and colleagues: BIG-bench collaborative language-model evaluation

What changed

Built a broad collaboratively contributed task suite and evaluation interface to characterize language-model behavior and scaling across diverse tasks.

Scientific scope

Built a broad collaboratively contributed task suite and evaluation interface to characterize language-model behavior and scaling across diverse tasks. Task composition, prompts, human baselines and brittle metrics influence observations. No universal scaling law or AGI certification is implied; only the general benchmark framework is acquired.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Task composition, prompts, human baselines and brittle metrics influence observations. No universal scaling law or AGI certification is implied; only the general benchmark framework is acquired.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

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

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction