ProactiveVideoQA AURA Study - TV 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 Mini59.4#781
2GPT-4.156.8#500
3Gemini 1.5 Pro52#1061
4MOSS-VL-Realtime50.2
5Gemini 2.0 Flash49.1#717
6InternLM-XComposer2.548.5#3981
7LLaVA-OneVision-7B45.1#2685
8InternVL2.5-8B41.5#2444
9LongVA-7B41.5#2788
10Qwen 2.5 VL 7B36.5#1838
11JoyAI-VL-Interaction34.6
12MMDuet (Harness: remove assistant turns)32.6
13MMDuet21.1
14VideoLLM-online-8B18.3

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-0-5 · How It Works · Data refreshed daily, snapshot 2026-11-16.