BoxComm (Punch Events) - Tactical: leaderboard
BoxComm boxing commentary generation when the requested category is tactical (analysis of strategy, technique and matchup dynamics), with video plus detected punch events as text as input. Percent of generated sentences that GPT-5.2 judges consistent with the reference commentary, higher is better.
Metric: Content consistency accuracy (%) on the sentences whose requested category is tactical (strategy, technique and matchup analysis); 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 February 2027. 3 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 28 | #1029 |
| 2 | LLaVA-OV-7B (BoxComm checkpoint unspecified) | 24.8 | |
| 3 | GPT-4o Mini | 22.2 | #1667 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=boxcomm-punch-events-tactical · How It Works · Data refreshed daily, snapshot 2026-11-21.