They do show their model as winning every category in Long Range Arena (LRA) ben... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		TheDudeMan on Feb 26, 2025 \| parent \| context \| favorite \| on: The FFT Strikes Back: An Efficient Alternative to ... 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.

yorwba on Feb 26, 2025 [–]

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.

Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact