PERCEIVE - Reader Behavior (Twitter): leaderboard

Metric: Reader behaviour prediction (Task C: predict repost-and-comment, repost or like from the comment and the author and commenter profiles), macro-F1 over the classes (times 100, so 0-100) on the held-out test split (8:1:1 partition) of PERCEIVE, reader-centric social-media data with real reader comments, behaviours and profiles, English Twitter subset; the model is prompted directly; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 3 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=perceive-reader-behavior-twitter · How It Works · Data refreshed daily, snapshot 2026-10-07.