Tay and colleagues: Long Range Arena sequence-model benchmark

What changed

Introduced a shared long-sequence test suite across text, images and mathematical expressions to compare efficient Transformer designs.

Scientific scope

Introduced a shared long-sequence test suite across text, images and mathematical expressions to compare efficient Transformer designs. Suite-specific model quality and efficiency are not proof of generally useful long-context reasoning. Record concerns benchmark construction, not a current leaderboard.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Suite-specific model quality and efficiency are not proof of generally useful long-context reasoning. Record concerns benchmark construction, not a current leaderboard.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Long Range Arena: A Benchmark for Efficient Transformers

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction