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
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 5.45 |
| 2 | MiniCPM-V-2.6 | 4.13 |
Interactive version: theaggregate.ai/benchmark?slug=omnistarpro-rng-offline-summary-fluency · How It Works · Data refreshed daily, snapshot 2026-09-26.