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

Question Answering on TriviaQA (test) (Acc and F1)

80.6F1 Score

IGPO

Updated 24d ago

Evaluation Results

Method	Links
IGPO 2025.10		80.6	-
DeepResearcher 2025.10		78.4	-
R1-searcher 2025.10		73.1	-
Search-r1-base 2025.10		71.9	-
CoT+RAG 2025.10		68.9	-
GiGPO 2025.10		64.7	-
Search-o1 2025.10		58.9	-
CoT 2025.10		45.6	-
Search-r1-instruct 2025.10		44.7	-
UR-RAG 2026.01		42.39	41.86
RePlug 2026.01		41.25	41.12
LURE-RAG 2026.01		40.47	40.57
LURE-RAG (w/o topics) 2026.01		40.01	40.08
k-shot 2026.01		39.78	39.76
0-shot 2026.01		35.87	35.66
UR-RAG 2026.01		34.72	36.76
RePlug 2026.01		33.21	36.03
LURE-RAG 2026.01		32.72	35.69
LURE-RAG (w/o topics) 2026.01		32.61	35.44
k-shot 2026.01		31.77	34.86
UR-RAG 2026.01		31.04	31.11
RePlug 2026.01		30.17	30.27
LURE-RAG 2026.01		30.1	29.68
LURE-RAG (w/o topics) 2026.01		29.73	29.47
k-shot 2026.01		26	28.41
0-shot 2026.01		22.14	27.79
0-shot 2026.01		21.37	22.58