BIG-bench (Beyond the Imitation Game Benchmark)

A collaborative suite of 200-plus wildly varied tasks from 450 authors; almost every number called BIG-bench today is really BIG-bench Hard or BIG-bench Lite.

Also known as: BIG-Bench, Beyond the Imitation Game Benchmark

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorycomposite
Subcategorycollaborative multi-task probe of language-model capabilities
Page statussuperseded
Metricnormalized preferred metric (task-specific; averaged across tasks)
Directionhigher_is_better
Unit%
Dataset licenceApache-2.0
PublisherGoogle (organizers); a 450-author, 132-institution open collaboration

What it measures

BIG-bench does not test one skill. It bundles more than 200 independently authored tasks -- 204 at publication, contributed by 450 authors across 132 institutions -- spanning linguistics, childhood development, mathematics, common-sense reasoning, biology, physics, social bias and software development, among others. The organizers deliberately solicited tasks believed to be beyond the capabilities of language models current at the time, so its coherence comes from a selection criterion (hardness for 2021-era models), not from a shared format or domain.

Task format

About 80% of tasks are JSON tasks: fixed lists of input/target examples, scored by a metric the task author chose (exact match, ROUGE, multiple-choice log-probability, and others), which also supports few-shot prompting. The remaining 20% are programmatic tasks written in Python that can query the model over several rounds and score it with custom code, such as the twenty_questions task. Each task author sets a preferred metric plus a high and low score anchor.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub