roberta-large

2 benchmarks · 2 observations · 2 sources

Scores at a glance

2 benchmarks · large dot: roberta-large; small dots: closest models where reported

roberta-large · LogiQA 2.0 & ReClor · test accuracy · official baselines ↗

CUAD (Contract Understanding Atticus Dataset) ↗48.2 AUPR points

RoBERTa-large · CUAD (Contract Understanding Atticus Dataset) · Area under precision-recall curve · original evaluation ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review — published result table ↗
Dan Hendrycks, Collin Burns, Anya Chen, Spencer Ball · 2021
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning ↗
Weihao Yu, Zihang Jiang, Yanfei Dong, Jiashi Feng · 2020

Names used in source tables

RoBERTa-large · roberta-large