NarrativeWorldBench
Explore score history ↗NarrativeWorldBench evaluates long-horizon narrative generation in audio drama across nine structural metrics and four Indic languages, across horizons from 10 to 200 episodes. Scoring is based on plot-beat F1 and other metrics.
- Released
- 2026-06-16
- Institutions
- University of California, Santa Barbara
- Evaluates
- General AI, Speech & Audio, cs.CL
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
NarrativeWorldBench paper
No reported scores are on record for this benchmark yet.