Skip to content
Weights Not Walls
Menu

SuperGLUE

Reported

A suite of English language understanding tasks such as question answering and inference.

Kind
Published by a third party's leaderboard, collected by Epoch AI. The leaderboard is named and linked.
Link
https://arxiv.org/pdf/1910.10683
Score shown
Epoch's column "Score", as a percentage, higher is better; random guessing scores about 0.0%. The source gives no error bars.
Results
10 in all: 2 for open-weight models, 1 for closed ones, 7 where Epoch does not say. 0 linked to a model page here.

Best open-weight result: T5-11B, 88.9%, number 1 of 10 results.

Open-weight rows are shaded. Dates are when the result was run or evaluated, where the data says. Data from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Epoch AI. Method