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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 Mini | 48.5 | #781 |
| 2 | GPT-4.1 | 45 | #500 |
| 3 | Gemini 1.5 Pro | 41.7 | #1061 |
| 4 | InternLM-XComposer2.5 | 41 | #3981 |
| 5 | Gemini 2.0 Flash | 40.4 | #717 |
| 6 | LLaVA-OneVision-7B | 38.2 | #2685 |
| 7 | InternVL2.5-8B | 36.5 | #2444 |
| 8 | LongVA-7B | 35.3 | #2788 |
| 9 | JoyAI-VL-Interaction | 33 | |
| 10 | Qwen 2.5 VL 7B | 32.7 | #1838 |
| 11 | MMDuet (Harness: remove assistant turns) | 28.2 | |
| 12 | MMDuet | 20.7 | |
| 13 | VideoLLM-online-8B | 17.8 |
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.