CourtSI-Ext: leaderboard
Metric: Overall score (%), question-weighted over the 13 CourtSI tasks, on CourtSI-Ext's 215 spatial questions from 111 pickleball broadcast frames (an unseen sport), answers read by exact format match from the model's raw output; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 55 | #105 |
| 2 | Qwen 3 VL 235B A22B | 47.9 | #228 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=courtsi-ext · How It Works · Data refreshed daily, snapshot 2026-10-11.