PERCEIVE - Reader Emotion (Twitter): leaderboard
Metric: Reader emotion prediction (Task A: classify a reader comment into one of seven emotions), 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 January 2027. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 | 53.34 |
Interactive version: theaggregate.ai/benchmark?slug=perceive-reader-emotion-twitter · How It Works · Data refreshed daily, snapshot 2026-10-07.