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

Long-form Question Answering on Summary-style queries

63.5Token-F1

HLTM

Updated 1mo ago

Evaluation Results

Method	Links
HLTM 2026.04		63.5	47.3	79.8
HLTM 2026.04		59.6	45.2	84.7
A-Mem 2026.04		59.5	48.5	67.2
RAG 2026.04		58.7	49.6	61.3
RAG 2026.04		58.6	46.8	69.1
Full-context 2026.04		58.4	46.1	77.4
RAG 2026.04		57.2	46.4	66.3
RAG 2026.04		57	47	60.2
ReadAgent 2026.04		56.6	42.5	77.1
RAG 2026.04		56.5	46.6	68.5
RAG 2026.04		55.8	46.5	59.6
RAPTOR 2026.04		53.6	44.4	62.2
Mem0 2026.04		52.6	40.8	59.7
RAG 2026.04		47.5	35.5	56.2
RAG 2026.04		45.9	35.6	60.2
RAG 2026.04		45.8	35.1	59.2
RAG 2026.04		45.7	35.2	61.8
RAG 2026.04		45.3	35	62.3
RAG 2026.04		45.1	34.1	56.7
RAPTOR 2026.04		44.1	32	59.5
A-Mem 2026.04		43	32.4	58.8
HippoRAG 2026.04		41.5	29.7	68.4
Full-context 2026.04		41.4	31.5	63.3
Mem0 2026.04		39.7	28.1	39.4
ReadAgent 2026.04		39.5	30	61.4
HippoRAG 2026.04		38.3	27.4	69.4
SimpleMem 2026.04		24.7	5.8	74.6
GraphRAG 2026.04		10.3	7.4	26.2
SimpleMem 2026.04		9.7	0.5	25.7