BoxComm (Punch Events) - Contextual: leaderboard

Metric: Content consistency accuracy (%) on the sentences whose requested category is contextual (fighter records, history, crowd); input video plus the 16 most recent detected punch events as text (the authors EIC-Gen input); category-conditioned commentary generation on BoxComm-Eval (the last 40 of 445 World Boxing Championship broadcast matches, 5.6K professional commentary sentences): from the 4 seconds of video before the target moment, the 8 previous commentary sentences and a requested category (play-by-play, tactical or contextual) the model writes one commentary sentence, and GPT-5.2 judges whether it conveys the core action or tactical meaning of the reference sentence; zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 3 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=boxcomm-punch-events-contextual · How It Works · Data refreshed daily, snapshot 2026-10-07.