RefereeBench - Foul Existence: leaderboard
Metric: Accuracy (%) on foul-existence questions (Q1), averaged across 11 sports; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 1.8 | 92.5 |
| 2 | Claude Haiku 4.5 | 81 |
| 3 | Gemini 3 Flash | 74.2 |
| 4 | Gemini 3 Pro | 71 |
| 5 | Claude Sonnet 4.5 | 65.4 |
| 6 | GPT-5 | 64.2 |
| 7 | GPT-4o | 63 |
Interactive version: theaggregate.ai/benchmark?slug=refereebench-foul-existence · How It Works · Data refreshed daily, snapshot 2026-10-07.