ProactiveVideoQA AURA Study - EGO Omega 0.5: leaderboard

The AURA 2.0 paper compares released models on streaming video interaction. IPIBench, StreamArena, ProactiveVideoQA and PhoStream retain their own protocols. ProactiveVideoQA reports PAUC; PhoStream’s overall score is question-weighted, and its timing categories are not guarantees of answer correctness. This board reports pAUC (native). Higher is better.

Metric: PAUC (native). Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-4.1 Mini65.8#781
2LLaVA-OneVision-7B61.6#2685
3GPT-4.158.8#500
4InternVL2.5-8B57.8#2444
5Gemini 2.0 Flash53.7#717
6MMDuet (Harness: remove assistant turns)52.2
7InternLM-XComposer2.550.3#3981
8Gemini 1.5 Pro49.7#1061
9MOSS-VL-Realtime47.8
10Qwen 2.5 VL 7B46.5#1838
11MMDuet46
12JoyAI-VL-Interaction41.2
13LongVA-7B37.4#2788
14VideoLLM-online-8B25

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=proactivevideoqa-aura-study-ego-omega-0-5 · How It Works · Data refreshed daily, snapshot 2026-11-16.