Leaderboard

This page tracks benchmark results for HybridRAG-Bench.

Summary

• Metric columns can be adapted to your final evaluation protocol.

• Higher is better unless a column explicitly states lower-is-better.

• Update tables by editing: docs/source/_static/leaderboard_arxiv_ai.csv, docs/source/_static/leaderboard_arxiv_cy.csv, docs/source/_static/leaderboard_arxiv_bio.csv.

Arxiv_AI

Rank	Date	Model	Method	Acc	Notes
1	2026-02-12	Llama-3.3-70B	HybridRAG	0.000	placeholder
2	2026-02-12	Llama-3.3-70B	KG-RAG	0.000	placeholder
3	2026-02-12	Llama-3.3-70B	RAG	0.000	placeholder
4	2026-02-12	Llama-3.3-70B	IO	0.000	placeholder

Arxiv_CY

Rank	Date	Model	Method	Acc	Notes
1	2026-02-12	Llama-3.3-70B	HybridRAG	0.000	placeholder
2	2026-02-12	Llama-3.3-70B	KG-RAG	0.000	placeholder
3	2026-02-12	Llama-3.3-70B	RAG	0.000	placeholder
4	2026-02-12	Llama-3.3-70B	IO	0.000	placeholder

Arxiv_BIO

Rank	Date	Model	Method	Acc	Notes
1	2026-02-12	Llama-3.3-70B	HybridRAG	0.000	placeholder
2	2026-02-12	Llama-3.3-70B	KG-RAG	0.000	placeholder
3	2026-02-12	Llama-3.3-70B	RAG	0.000	placeholder
4	2026-02-12	Llama-3.3-70B	IO	0.000	placeholder

Submission Format

Use this schema when adding new results:

• Date: YYYY-MM-DD

• Model: Model name and size

• Method: IO, RAG, KG-RAG, HybridRAG, etc.

• Acc: Primary accuracy metric

• Notes: Optional details (retriever, hops, or config)