OmniStarPro-RNG (Offline) - Summary Fluency: leaderboard

Metric: Summary fluency (0-10; GPT-4o judge rating of the concatenated narration against the ground-truth narrative on logicality, fluency, conciseness, semantic consistency and completeness; responses decoded at prescribed timestamps). Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.

Top models

#ModelScore
1GPT-4o5.45
2MiniCPM-V-2.64.13

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