LatentMD Benchmark
Explore score history ↗Evaluates Markdown boundary failures, specifically CommonMark-level fence-boundary accuracy, across 4,179 prompts using a scoring CLI that separates content correctness from boundary correctness.
- Released
- 2026-09-07
- Institutions
- Seoul National University
- Evaluates
- Code & Software, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
LatentMD paper
No reported scores are on record for this benchmark yet.