PhoStream AURA Study - Backward: 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

#ModelScoreOverall rank
1Gemini 3 Pro82.19#136
2Seed 1.877.31#245
3Qwen 3 Omni 30B A3B77.24#870
4Qwen 3 VL 8B71.5#899
5Qwen 3 VL 30B A3B69.46#794
6MOSS-VL-Realtime65.54
7Qwen2.5-Omni-7B65.2#1866
8Seed-1.662.94#453
9Qwen 3.5 9B62.92#814
10JoyAI-VL-Interaction59.48
11Dispider42.9#4338
12VideoLLM-online-8B24.72
13MMDuet28.3

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