RefereeBench: leaderboard

Metric: Overall accuracy (%) of multiple-choice sports-refereeing questions over 925 officiating videos in 11 sports (6,475 QA pairs), averaged across sports, full video at 720p; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 11 models tracked.

Top models

#ModelScore
1Seed 1.861.1
2Gemini 3 Flash60.6
3Gemini 3 Pro60
4GPT-554.8
5Claude Sonnet 4.547.6
6GPT-4o47.1
7Claude Haiku 4.545.6

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