PhoStream AURA Study - Partly Correct: 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 native forward timing rate (%). Higher is better.
Metric: Native forward timing rate (%). Source: arxiv.org. Saturation forecast: Around June 2027. 13 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed-1.6 | 56.85 | #453 |
| 2 | Seed 1.8 | 41.18 | #245 |
| 3 | MOSS-VL-Realtime | 29.62 | |
| 4 | Gemini 3 Pro | 20.77 | #136 |
| 5 | Qwen 3.5 9B | 15.77 | #814 |
| 6 | Qwen2.5-Omni-7B | 13.85 | #1866 |
| 7 | MMDuet2 | 12.24 | |
| 8 | Qwen 3 VL 8B | 11.06 | #899 |
| 9 | Dispider | 10.28 | #4338 |
| 10 | Qwen 3 VL 30B A3B | 7.49 | #794 |
| 11 | JoyAI-VL-Interaction | 3.75 | |
| 12 | Qwen 3 Omni 30B A3B | 2.03 | #870 |
| 13 | VideoLLM-online-8B | 0.04 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=phostream-aura-study-partly-correct · How It Works · Data refreshed daily, snapshot 2026-11-16.