Generative Embedding Benchmark
Explore score history ↗GEB evaluates embeddings by measuring answer-relevant content recoverable by a decoder, using a visual question-answering dataset with development and test splits, and scoring answer quality.
- Released
- 2026-08-07
- Institutions
- Fudan University · Kuaishou (China) · University of Science and Technology of China
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
Generative Embedding Benchmark paper
No reported scores are on record for this benchmark yet.