ProactiveVideoQA AURA Study - TV Omega 0: 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. 13 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-4.1 Mini48.5#781
2GPT-4.145#500
3Gemini 1.5 Pro41.7#1061
4InternLM-XComposer2.541#3981
5Gemini 2.0 Flash40.4#717
6LLaVA-OneVision-7B38.2#2685
7InternVL2.5-8B36.5#2444
8LongVA-7B35.3#2788
9JoyAI-VL-Interaction33
10Qwen 2.5 VL 7B32.7#1838
11MMDuet (Harness: remove assistant turns)28.2
12MMDuet20.7
13VideoLLM-online-8B17.8

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-tv-omega-0 · How It Works · Data refreshed daily, snapshot 2026-11-16.