Single-hop Question Answering

Benchmarks

Dataset Name	SOTA Method	Metric
PopQA	SDGA-Phase	EM73.6	200	17d ago
TriviaQA	Dep-Search	EM72	147	17d ago
LoCoMo	ShardMemo	F10.6408	111	2mo ago
NQ	Tree-GRPO	Exact Match (EM)51.7	60	2mo ago
TriviaQA (test)	GIGPO w/ PaW	Accuracy66	60	18d ago
PopQA (test)	ZeroSearch	Accuracy51.5	43	18d ago
NQ	MultiSearch	Accuracy49.1	37	2mo ago
Single-hop QA Average	MemPO	F1 Score59.61	35	4mo ago
Natural Questions (NQ) (test)	SE-Search-3B	EM47.5	33	4mo ago
Trivia	Tree-GRPO	Exact Match68.1	30	4mo ago
LoCoMo Single-Hop	MEMMA_LM	F1 Score50.45	24	22d ago
PopQA out-of-domain	GEPO	Accuracy52.4	24	1mo ago
LoCoMo Single-Hop (test)		F137.9	24	4mo ago
NQ (test)	GRPO w/ PaW	Accuracy48.9	22	18d ago
MFQA en 16k	DCS	Overall Score23.76	22	4mo ago
Qasper	Llama-3-8B-Instruct	Score44.79	22	4mo ago
NarrativeQA	DCS	Score23.89	22	4mo ago
MFQA en	Llama-3-8B-Instruct with DCS	Score45.83	22	4mo ago
NQ (Natural Questions) (test)	InfoReasoner-3B	Accuracy45.3	21	4mo ago
SQuAD		F1 Score86.8	21	4mo ago
NQ (Natural Questions) in-domain (test)	ARPO	EM31.45	20	4mo ago
TriviaQA (out-of-domain)	GEPO	Accuracy68	19	1mo ago
NQ (in-domain)	GEPO	Accuracy48.2	19	1mo ago
Factrecall en	LM-infinite	Score31.36	17	4mo ago
Loogle SD	DCS	Score45.1	17	4mo ago

Showing 25 of 40 rows