Benchmark Almanac

BAREC organizers

We track 2 benchmarks that BAREC organizers made or helped make.

0 in use 2 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
BAREC Shared Task 2025 Models assign Arabic sentences and documents to 19 reading levels. The hardest sentence determines the reference level for a document. Reading in many languages May 2025 Not in cards
BAREC-ST-2026 Models assign Arabic sentences and documents to 19 reading levels. The blind test includes texts from 17 publishers absent from the original corpus. Reading in many languages May 2026 Not in cards