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

Retrieval-Augmented Generation on All Datasets Aggregated

76.6Average Performance Score

GuarantRAG

Updated 8d ago

Evaluation Results

Method	Links
GuarantRAG 2026.04		76.6	20.6
GuarantRAG 2026.04		76.2	21
GuarantRAG 2026.04		75.8	21.2
GuarantRAG 2026.04		75.2	21.8
P-RAG 2026.04		74.1	23.5
P-RAG 2026.04		73.7	23.9
P-RAG 2026.04		73.3	24.1
SOLAR 2026.04		73.2	24.5
P-RAG 2026.04		72.8	24.6
SOLAR 2026.04		72.8	24.9
SOLAR 2026.04		72.4	25.1
DRAGIN 2026.04		72.3	24.9
SOLAR 2026.04		71.9	25.7
DRAGIN 2026.04		71.9	25.3
FLARE 2026.04		71.8	25.3
DRAGIN 2026.04		71.6	25.5
RQ-RAG 2026.04		71.6	25.8
FLARE 2026.04		71.4	25.7
RQ-RAG 2026.04		71.2	26.1
DRAGIN 2026.04		71.1	26
FLARE 2026.04		71.1	25.9
RQ-RAG 2026.04		70.8	26.4
FLARE 2026.04		70.6	26.4
RQ-RAG 2026.04		70.4	26.9
SelfRAG 2026.04		69.8	27.1
SelfRAG 2026.04		69.4	27.5
SelfRAG 2026.04		69.1	27.8
DA-RAG 2026.04		68.9	27.8
SelfRAG 2026.04		68.7	28.2
DA-RAG 2026.04		68.5	28.2
DA-RAG 2026.04		68.2	28.4
DA-RAG 2026.04		67.8	28.9
Standard RAG 2026.04		65.1	30.2
Standard RAG 2026.04		64.8	30.6
Standard RAG 2026.04		64.3	30.8
Standard RAG 2026.04		64	31.4
Qwen3-14B-T 2026.04		59.5	32.9
Qwen3-14B-T 2026.04		59.5	32.9
Qwen3-14B-T 2026.04		59.5	32.9
Qwen3-14B-T 2026.04		59.5	32.9