Pro2Bench: leaderboard
Metric: Proactive Quality Score (PQS, 0-1 scaled to %): per decision point, 1 for correct silence, the GPT-5.2-judged guidance quality (rescaled 0-1) for a correctly timed interrupt, 0 for spurious or missed interrupts; 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 2034. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 27B | 37 |
| 2 | Gemini 3.1 Pro (Preview) | 35 |
| 3 | Llama 4 Maverick | 35 |
| 4 | Claude Opus 4.6 | 32 |
| 5 | Qwen 3 VL 235B A22B | 30 |
Interactive version: theaggregate.ai/benchmark?slug=pro2bench · How It Works · Data refreshed daily, snapshot 2026-09-29.