The successor to GLUE — a suite of difficult language understanding tasks including reading comprehension, textual entailment, and word sense disambiguation.
This definition has not completed editorial and provenance review. Verify its metric, version, source, and evaluation configuration upstream before using it for a model-selection decision.
Well-established NLU benchmark. Broad coverage of language understanding capabilities.
Largely saturated — human baseline was surpassed years ago. In training data for all current models. No score data currently.
Higher is better. Aggregate accuracy (0–100).
Largely saturated — human baseline was surpassed years ago.
No scores available for this benchmark yet.