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

Question Answering on NQ (Accuracy)

66.6Accuracy

Vanilla RAG

Updated 4d ago

Evaluation Results

Method	Links
Vanilla RAG 2025.09		66.6
MIS 2025.09		66
MIS 2025.09		65.4
InstructRAG 2025.09		64
AstuteRAG 2025.09		62.2
RobustRAG 2025.09		60.4
InstructRAG 2025.09		60.2
MIS 2025.09		60.2
MIS 2025.09		60
MIS 2025.09		59.6
RobustRAG 2025.09		59.4
MIS 2025.09		59
AstuteRAG 2025.09		59
Vanilla RAG 2025.09		58.4
MIS 2025.09		58
AstuteRAG 2025.09		58
RobustRAG 2025.09		57.6
MIS 2025.09		57
Vanilla RAG 2025.09		56.2
AstuteRAG 2025.09		56.2
AstuteRAG 2025.09		55.4
MIS 2025.09		54.8
InstructRAG 2025.09		54.8
ASTUTE RAG 2024.10		52.2
RobustRAG 2025.09		52.2
InstructRAG 2025.09		51.4
RobustRAG 2025.09		51.4
USC 2024.10		51.2
RobustRAG 2025.09		50.4
ASTUTE RAG 2024.10		50.2
ASTUTE RAG 2024.10		50.2
RankCoT 2025.02		49.98
AstuteRAG 2025.09		49.8
InstructRAG 2025.09		49.4
RankCoT 2025.02		48.78
USC 2024.10		48.1
RobustRAG 2024.10		47.8
No Refinement 2025.02		47.66
Self-Route 2024.10		47.5
Self-Route 2024.10		47.5
RankCoT 2025.02		47.41
No RAG 2024.10		47.1
InstructRAG 2024.10		47.1
InstructRAG 2024.10		46.8
No RAG 2024.10		46.8
USC 2024.10		46.4
RobustRAG 2025.09		46.4
Rerank 2025.02		46.18
CDKC 2026.02		45.7
No Refinement 2025.02		45.68
InstructRAG 2024.10		45.4
Self-Route 2024.10		45.4
CoT 2025.02		45.33
GRPO 2026.02		45.27
GenRead 2024.10		45.1
No RAG 2024.10		44.8
RAG (Open-domain) 2023.02		44.5
RAG 2024.10		44.4
RobustRAG 2025.09		44.4
Summary 2025.02		44.27
RobustRAG 2025.09		44
RAG 2024.10		43.1
RAG 2024.10		42.7
RobustRAG 2024.10		42.7
ASTUTE RAG 2024.10		42.7
No Refinement 2025.02		42.51
GenRead 2024.10		42
Self-Route 2024.10		41.4
Vanilla RAG 2025.09		41
GenRead 2024.10		40.7
Vanilla RAG 2025.09		40
RAG 2024.10		39.3
RAG 2026.02		38.97
InstructRAG 2025.09		38.8
GenRead 2024.10		38.6
InstructRAG 2024.10		38.3
Vanilla RAG 2025.09		37.4
AstuteRAG 2025.09		36.4
RobustRAG 2024.10		35.6
RobustRAG 2024.10		34.2
RAG 2026.02		33.37
Vanilla RAG 2025.09		31.2
CGKE 2026.02		30.6
CDKC 2026.02		30.33
CoT 2026.02		29.83
No RAG 2024.10		29.8
GRPO 2026.02		29.73
USC 2024.10		29.5
Vanilla SFT 2026.02		26.3
T5-base (Closed-Book) 2023.02		25.9
Vanilla LLM 2026.02		24.6
InstructRAG 2025.09		24.2
InstructRAG 2025.09		20.8
CGKE 2026.02		18.83
CoT 2026.02		17.73
Vanilla SFT 2026.02		17.47
AstuteRAG 2025.09		15.6
Vanilla LLM 2026.02		14.77
InstructRAG 2025.09		13.8
Vanilla RAG 2025.09		13.6

Showing 100 of 108 rows