RefereeBench - Temporal Grounding: 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 accuracy in percent on questions about when the infraction happens in the video, averaged across sports; higher is better.

Metric: Accuracy (%) on temporal-grounding questions (Q7), averaged across 11 sports; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Seed 1.850.1#252
2Gemini 3 Pro48.8#145
3Gemini 3 Flash46.8#175
4Qwen 3 VL 8B39#917
5GPT-538.1#178
6Claude Haiku 4.534.5#583
7Claude Sonnet 4.533.3#261
8VideoLLaMA3-7B30.1#2050
9InternVL3.5-8B29.6#1604
10GPT-4o28.6#751
11LLaVA-Video-7B27.8#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-temporal-grounding · How It Works · Data refreshed daily, snapshot 2026-11-21.