Post

Kaggle
@kaggle.com

1H-VideoQA is now available on Kaggle Benchmarks! Developed by Google DeepMind back in 2024 (Antoine Yang) and now updated with latest SOTA models, 1H-VideoQA is a 101-prompt benchmark for long-context video comprehension and temporal episodic reasoning across hour-long YouTube footage.

Kaggle
@kaggle.com

Top of the leaderboard: 🥇Gemini 3.5 Flash: 80.2% 🥈Gemini 3 Flash Preview: 79.2% 🥉Gemini 2.5 Pro: 78.9% Models must process raw frames as native tokens to locate seconds-long events hidden in an hour of video; accuracy scales logarithmically with frame density.

0 reposts0 likes