OmniStarPro-RNG (Online) - Summary Fluency: leaderboard

Metric: Summary fluency (0-10; GPT-4o judge rating of the concatenated self-timed narration against the ground-truth narrative on logicality, fluency, conciseness, semantic consistency and completeness). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 5 models tracked.

Top models

#ModelScore
1LiveStarPro4.41
2LiveStar4.25
3MMDuet2.69
4VideoLLM-online0.59
5VideoLLM-MoD0.55

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