Share your thoughts, 1 month free Claude Pro on usSee more

Knowledge-grounded Dialogue on Wizard of Wikipedia (WoW)

78.6Performance Score

o1

Updated 8d ago

Evaluation Results

Method	Links
o1 2026.04		78.6
GuarantRAG 2026.04		77.8
GPT-4o 2026.04		77.2
GuarantRAG 2026.04		76.2
GuarantRAG 2026.04		75.1
P-RAG 2026.04		74.3
P-RAG 2026.04		73.8
SOLAR 2026.04		72.4
SOLAR 2026.04		72.1
DRAGIN 2026.04		72
DRAGIN 2026.04		71.6
FLARE 2026.04		71.5
P-RAG 2026.04		71.2
FLARE 2026.04		71.2
RQ-RAG 2026.04		70.9
RQ-RAG 2026.04		70.4
SOLAR 2026.04		69.5
SelfRAG 2026.04		69.3
DRAGIN 2026.04		69.1
SelfRAG 2026.04		68.9
FLARE 2026.04		68.7
DA-RAG 2026.04		68.2
RQ-RAG 2026.04		68.1
DA-RAG 2026.04		67.8
SelfRAG 2026.04		66.8
DA-RAG 2026.04		65.4
Standard RAG 2026.04		65.1
Standard RAG 2026.04		64.7
Standard RAG 2026.04		62.7
Qwen3-14B-T 2026.04		59.3
Qwen3-14B 2026.04		58.7
Qwen3-8B 2026.04		56.2