NARU Benchmark
Explore score history ↗NARU evaluates multimodal models on Japanese long-form video understanding across narrative evolution (character evolution, sequential flow, plot progression, thematic development) and cultural nuance (aizuchi, reading the air, subtext, cultural context, sentiment) via multiple-choice QA.
- Released
- 2026-08-13
- Institutions
- The University of Tokyo · Kyushu University
- Evaluates
- General AI, Reasoning, Vision & 3D
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
NARU paper and code
No reported scores are on record for this benchmark yet.