RefereeBench - Temporal Grounding: leaderboard

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

Top models

#ModelScore
1Seed 1.850.1
2Gemini 3 Pro48.8
3Gemini 3 Flash46.8
4GPT-538.1
5Claude Haiku 4.534.5
6Claude Sonnet 4.533.3
7GPT-4o28.6

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