Text Summarization on MENSA

Metric: ROUGE-1 (higher is better)

LeaderboardDataset
Loading chart...
#ModelROUGE-1Extra DataPaperDateCode
1NexusSum (Mistral Large)44.91NoNexusSum: Hierarchical LLM Agents for Long-Form ...2025-05-30-
2Zero-Shot (Mistral Large)37.43NoNexusSum: Hierarchical LLM Agents for Long-Form ...2025-05-30-
3Hierarchically Merging and Agent Refinement31.31NoAgent-as-Judge for Factual Summarization of Long...2025-01-17Code