RefereeBench: leaderboard

RefereeBench (2026) tests multimodal models as sports referees on 925 officiating videos across 11 sports with 6,475 human-annotated multiple-choice questions. This board is overall accuracy in percent, averaged across sports over the seven question types; higher is better.

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 February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Seed 1.861.1#252
2Gemini 3 Flash60.6#175
3Gemini 3 Pro60#145
4GPT-554.8#178
5Claude Sonnet 4.547.6#261
6GPT-4o47.1#751
7Qwen 3 VL 8B47.1#917
8Claude Haiku 4.545.6#583
9InternVL3.5-8B41.8#1604
10VideoLLaMA3-7B36#2050
11LLaVA-Video-7B27.4#2276

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=refereebench · How It Works · Data refreshed daily, snapshot 2026-11-21.