OmniPro - Event Alert: leaderboard

OmniPro (2026) evaluates proactive streaming video understanding: from continuous audio-visual streams of 2,700 human-verified questions, a model must decide when to respond and what to say across nine sub-tasks. In probe mode the model is queried just before and just after each trigger and scores only when both answers are right; this board is the probe accuracy in percent on alerting the moment a specified instantaneous event occurs, higher is better.

Metric: Probe-mode accuracy (%): for each ground-truth trigger the model, given the video so far, is queried 2-5 s before (expecting a negative answer) and 0-3 s after (expecting the task answer, exact match on a structured output), and the trigger counts only if both are right, on the instant event alert (alert the moment a specified sound or visual event occurs) sub-task of OmniPro (2,700 human-verified proactive streaming questions on LongVALE and COIN videos, 84% needing audio; 1 fps input); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1video-SALMONN-2+ 7B37.2#2322
2Qwen2.5-Omni-7B35.4#1884
3VideoLLaMA2.1-7B-AV21.8#4204
4Qwen 3 Omni 30B A3B21.5#847
5MiniCPM-o-4.518.2#1252
6Phi-4 Multimodal Instruct13.7#4154
7Qwen 3 VL 8B7.5#917
8InternVL3.5-8B4.8#1604

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=omnipro-event-alert · How It Works · Data refreshed daily, snapshot 2026-11-21.