OmniStarPro-RNG (Online): leaderboard

Metric: Semantic correctness (0-10; GPT-4o judge score of the earliest response in each ground-truth clip, mean of semantic accuracy, language quality and information completeness; the model decides by itself when to speak, 1,000 evaluation streams of the OmniStarPro-Live partition). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 5 models tracked.

Top models

#ModelScore
1LiveStarPro3.27
2LiveStar3.19
3MMDuet1.93
4VideoLLM-online1.68
5VideoLLM-MoD1.66

Interactive version: theaggregate.ai/benchmark?slug=omnistarpro-rng-online · How It Works · Data refreshed daily, snapshot 2026-09-26.