Hacker News Reader

They do show their model as winning every category in Long Range Arena (LRA) benchmark. Hopefully they have not excluded losing categories or better models.

View on HN

Winning against their own baseline, not against the current best-performing model. Which apparently is S5 currently https://paperswithcode.com/sota/long-range-modeling-on-lra with 87.46 overall vs. 58.31 here.

Reply on news.ycombinator.com