WSC

PaLM 2-L 86.9%

PaLM (540B) 95.9% leads since April 2022

Dropped

Labs’ own numbers All independent runs Include claimed scores

Models decide whether a pronoun refers to a given noun phrase in sentences that need commonsense to resolve. Scored by accuracy.

This is the SuperGLUE recasting of the Winograd Schema Challenge.

Made by: NYU, Facebook AI, University of Washington, and DeepMind (SuperGLUE)
Released: May 2019
Kind: Commonsense
Level: Everyday
Scored: Checked automatically
Answers: Multiple choice
Tasks: All public

Strongest model tested: PaLM 2-L #195 on the capability index
Last in a launch post: May 2023, dropped after it saturated
Last model added: May 2023
Scores refreshed: November 12th, 2026

Model scored in lab cards

Launch post lists it, from 1 lab

PaLM 2-L leads with 86.9%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

PaLM (540B) leads with 95.9% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

PaLM (540B) leads with 95.9%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

Bars Table

86.9 PaLM 2-L

1 PaLM 2-L 86.9%

Source: Labs’ model cards

1 PaLM (540B) 95.9%
2 T5-11B 93.8%
3 GPT-3 175B (davinci) 80.1%

Source: Official WSC leaderboard

1 PaLM (540B) 95.9%
2 T5-11B 93.8%
3 PaLM 2-L 86.9%
4 GPT-3 175B (davinci) 80.1%

Sources: Official WSC leaderboard and labs’ model cards

#	Model	Score	Setting	Date	Source
1	PaLM 2-L	86.9%		May 2023	Lab model card

#	Model	Score	Date	Source
1	PaLM (540B)	95.9%	Apr 2022	Official leaderboard
2	T5-11B	93.8%	Oct 2019	Official leaderboard
3	GPT-3 175B (davinci)	80.1%	May 2020	Official leaderboard

#	Model	Score	Date	Source
1	PaLM (540B)	95.9%	Apr 2022	Official leaderboard
2	T5-11B	93.8%	Oct 2019	Official leaderboard
3	PaLM 2-L	86.9%	May 2023	Lab model card
4	GPT-3 175B (davinci)	80.1%	May 2020	Official leaderboard

The benchmark's own leaderboard has 26 entries, 3 of them models we track. Switch the scores above to rank them together.

Number one over time Number one over time Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind

Own leaderboard Passed 85% in Oct 2019, by T5-11B

PaLM (540B) 95.9%

Source: Official WSC leaderboard

T5-11B on the official leaderboard passed 85% in October 2019

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official WSC leaderboard and labs’ model cards

Labs dropped it from launch posts once the best score passed 85%

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.