LEVANTE-bench
Explore score history ↗LEVANTE-bench evaluates vision-language models on six cognitive tasks from the LEVANTE dataset, comparing model performance and error patterns with children aged 5-12 across three countries.
- Released
- 2026-06-03
- Institutions
- Stanford University
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
LEVANTE-bench paper
No reported scores are on record for this benchmark yet.