IPIBench - Reactive-under-Proactive: leaderboard

Metric: Accuracy (%) on reactive-under-proactive interaction (answer a query while a proactive task stays active), on IPIBench (1,831 videos, 3,738 interaction instances from egocentric and exocentric datasets) under a unified streaming protocol at 1 FPS (offline models see a sliding window of the latest 16 frames); a proactive response counts only if the first trigger falls within one second of the ground-truth moment, multi-turn tasks only if every required trigger and answer is correct, reactive answers by bidirectional substring matching against up to 20 reference answers; higher is better. Source: arxiv.org. Saturation forecast: Around February 2028. 11 models tracked.

Top models

#ModelScore
1Qwen 3.5 Plus22.01
2GPT-4o17.68
3Gemini 3 Pro17.68
4Gemini 2.5 Pro17.54
5GPT-5.415.06
6GLM-4.6V6.77
7InternVL3-8B0

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