Benchmark Almanac

ArAIEval organizers

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

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

Benchmarks

Name Kind Released Best score Status
ArAIEval 2023 Models identify persuasion techniques in Arabic posts and news paragraphs. They also classify posts for disinformation. Reading in many languages Jun 2023 Not in cards
ArAIEval 2024 Models mark persuasive passages in Arabic text and name the technique. They also classify Arabic memes using the image, its extracted text, or both. Reading in many languages Mar 2024 Not in cards