PhoStream AURA Study - Instant: 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 evaluation score (0-100). Higher is better.
Metric: Native evaluation score (0-100). Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 80.83 | #136 |
| 2 | Seed 1.8 | 80.45 | #245 |
| 3 | Qwen 3 Omni 30B A3B | 77.18 | #870 |
| 4 | Qwen 3 VL 8B | 75.22 | #899 |
| 5 | Qwen 3 VL 30B A3B | 73.38 | #794 |
| 6 | MOSS-VL-Realtime | 72.69 | |
| 7 | Qwen 3.5 9B | 72.13 | #814 |
| 8 | Seed-1.6 | 71.28 | #453 |
| 9 | JoyAI-VL-Interaction | 68.35 | |
| 10 | Qwen2.5-Omni-7B | 67.71 | #1866 |
| 11 | Dispider | 44.24 | #4338 |
| 12 | VideoLLM-online-8B | 24.88 | |
| 13 | MMDuet2 | 8.76 |
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-instant · How It Works · Data refreshed daily, snapshot 2026-11-16.