IPIBench - Interleaved Reactive-Proactive Requests: leaderboard
Metric: Accuracy (%) on the interleaved reactive-proactive request tasks (mean of reactive-to-proactive, reactive-under-proactive and reactive-after-proactive), 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 September 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 Plus | 28.28 |
| 2 | GPT-5.4 | 23.79 |
| 3 | GPT-4o | 23.63 |
| 4 | Gemini 3 Pro | 23.04 |
| 5 | GLM-4.6V | 22.76 |
| 6 | Gemini 2.5 Pro | 22.32 |
| 7 | InternVL3-8B | 5.5 |
Interactive version: theaggregate.ai/benchmark?slug=ipibench-interleaved-reactive-proactive-requests · How It Works · Data refreshed daily, snapshot 2026-10-07.