Text Summarization on MENSA

Metric: ROUGE-L (higher is better)

LeaderboardDataset
Loading chart...
#ModelROUGE-LExtra DataPaperDateCode
1Zero-Shot (Mistral Large)21.52NoNexusSum: Hierarchical LLM Agents for Long-Form ...2025-05-30-
2NexusSum (Mistral Large)19.23NoNexusSum: Hierarchical LLM Agents for Long-Form ...2025-05-30-
3Hierarchically Merging and Agent Refinement18.62NoAgent-as-Judge for Factual Summarization of Long...2025-01-17Code