Our new X account is live! Follow @wizwand_team for updates

Question Answering on NQ (Natural Questions) (test)

68.6Accuracy

Sampling + MIS

Updated 4d ago

Evaluation Results

Method	Links
Sampling + MIS 2025.09		68.6
Sampling + MIS 2025.09		68.6
Sampling + MIS 2025.09		67.4
InstructRAG 2025.09		65.8
Vanilla RAG 2025.09		65.4
AstuteRAG 2025.09		64.2
InstructRAG 2025.09		63.8
RobustRAG 2025.09		63.4
RobustRAG 2025.09		63.4
RobustRAG 2025.09		63
Sampling + MIS 2025.09		62.8
Vanilla RAG 2025.09		60.8
Sampling + MIS 2025.09		60.8
RobustRAG 2025.09		60.6
Sampling + MIS 2025.09		60
AstuteRAG 2025.09		59.6
Sampling + MIS 2025.09		59
AstuteRAG 2025.09		58.2
Sampling + MIS 2025.09		58
AstuteRAG 2025.09		57.2
Sampling + MIS 2025.09		56
AstuteRAG 2025.09		55.6
Sampling + MIS 2025.09		55.4
Vanilla RAG 2025.09		55.2
Vanilla RAG 2025.09		55
InstructRAG 2025.09		54.6
RobustRAG 2025.09		54.4
AstuteRAG 2025.09		54.2
RobustRAG 2025.09		53.6
RobustRAG 2025.09		53.4
RobustRAG 2025.09		52.8
Sampling + MIS 2025.09		51.6
Sampling + MIS 2025.09		50.4
InstructRAG 2025.09		49.6
Vanilla RAG 2025.09		49.4
InstructRAG 2025.09		49.4
InstructRAG 2025.09		48.2
AstuteRAG 2025.09		47.6
RobustRAG 2025.09		47.4
RobustRAG 2025.09		47
RobustRAG 2025.09		46.6
RobustRAG 2025.09		46.4
InstructRAG 2025.09		46
AstuteRAG 2025.09		43.6
Vanilla RAG 2025.09		40.4
Vanilla RAG 2025.09		39.4
InstructRAG 2025.09		37.8
AstuteRAG 2025.09		37.2
Vanilla RAG 2025.09		30.2
InstructRAG 2025.09		27.6
AstuteRAG 2025.09		26
AstuteRAG 2025.09		22.4
Vanilla RAG 2025.09		20.6
Vanilla RAG 2025.09		15.2
InstructRAG 2025.09		14.2
Vanilla RAG 2025.09		13.8
InstructRAG 2025.09		13.4
Vanilla RAG 2025.09		11.8
InstructRAG 2025.09		11.4
AstuteRAG 2025.09		10.6