Visual RAG Benchmark
Explore score history ↗Visual RAG Benchmark evaluates end-to-end retrieval-augmented generation on reference tables from three EU Water Framework Directive guidance documents, scoring answers on 103 and 154 question sets split into text and table question types via LLM-as-a-judge correctness, ROUGE-1, and retrieval accuracy across seven indexing and retrieval pipelines.
- Released
- 2026-09-10
- Evaluates
- Finance, Information retrieval, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
Visual RAG Benchmark code
No reported scores are on record for this benchmark yet.