Pro2Bench - Intervention Timing: leaderboard
Metric: Geometric mean of the interrupt-class and silent-class F1 (G-Mean F1, 0-1 scaled to %) for deciding when to speak; zero-shot monolithic assistant (8 uniformly sampled frames per clip, greedy decoding for the interrupt or silent decision), mean over the six evaluation sets (EgoExo4D, EPIC-KITCHENS, HowTo100M, Ego4D, HoloAssist, EgoProactive); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 51 |
| 2 | Gemini 3.1 Pro (Preview) | 48 |
| 3 | Llama 4 Maverick | 45 |
| 4 | Qwen 3 VL 235B A22B | 43 |
| 5 | Qwen 3.6 27B | 31 |
| 6 | GPT-5.2 | 7 |
Interactive version: theaggregate.ai/benchmark?slug=pro2bench-intervention-timing · How It Works · Data refreshed daily, snapshot 2026-09-29.