List your company

Question Answering on HotpotQA (test) (EM Metric)

57.2EMIdeal Model Selection
11.54423.39735.2547.103Oct 13, 2025Oct 21, 2025Oct 29, 2025Nov 6, 2025Nov 14, 2025Nov 22, 2025Dec 1, 2025

Evaluation results

MethodLinks
Ideal Model SelectionCategory=Baseline2025.1057.2
R2CSelectCategory=Model Selection RAR2025.1050.2
RAGEnsembleCategory=Model Selection RAR2025.1046
R2CSelectCategory=Model Selection RAR, Variant=w/o clustering2025.1044
Search-R1Category=Retrieval-Augmented Reasoning (RAR)2025.1041.4
RAGEnsembleCategory=Model Selection RAR, Variant=w/o clustering2025.1040.8
ReSearchCategory=Retrieval-Augmented Reasoning (RAR)2025.1038.8
INSPOBackbone=Qwen-2.5-3B, Category=Tool-integrated Methods2025.1237.7
RAGEnsembleCategory=Model Selection RAR, Variant=w/o clus. & conf.2025.1037.2
INSPOBackbone=Qwen-2.5-7B, Category=Tool-integrated Methods2025.1236.8
LLMBlenderCategory=Model Selection RAR2025.1036
Search-R1Backbone=Qwen-2.5-7B, Category=Tool-integrated Methods2025.1235.6
SFTBackbone=Qwen-2.5-7B, Category=Tool-integrated Methods2025.1233.1
SelfAskCategory=Retrieval-Augmented Reasoning (RAR)2025.1033
LLMBlenderCategory=Model Selection RAR, Variant=w/o clustering2025.1031.8
RandomCategory=Model Selection RAR2025.1031.6
Search-R1Backbone=Qwen-2.5-3B, Category=Tool-integrated Methods2025.1230.9
RAGBackbone=Qwen-2.5-7B, Category=Tool-integrated Methods2025.1229.9
Search-o1Category=Retrieval-Augmented Reasoning (RAR)2025.1029
ReActCategory=Retrieval-Augmented Reasoning (RAR)2025.1027.8
IRCoTCategory=Vanilla LLM & RAG2025.1027.2
LLMBlenderCategory=Model Selection RAR, Variant=w/o clus. & conf.2025.1026
RAGBackbone=Qwen-2.5-3B, Category=Tool-integrated Methods2025.1225.5
FLARECategory=Vanilla LLM & RAG2025.1025.2
GRPOBackbone=Qwen-2.5-7B, Category=Model Inference2025.1224.2
SFTBackbone=Qwen-2.5-3B, Category=Tool-integrated Methods2025.1224
DRAGINCategory=Vanilla LLM & RAG2025.1023.2
CoTCategory=Vanilla LLM & RAG2025.1022.2
Search-o1Backbone=Qwen-2.5-3B, Category=Tool-integrated Methods2025.1222.1
SFTBackbone=Qwen-2.5-7B, Category=Model Inference2025.1221.7
DirectCategory=Vanilla LLM & RAG2025.1020.8
GRPOBackbone=Qwen-2.5-3B, Category=Model Inference2025.1220.1
Search-o1Backbone=Qwen-2.5-7B, Category=Tool-integrated Methods2025.1218.7
SFTBackbone=Qwen-2.5-3B, Category=Model Inference2025.1218.6
Vanilla RAGCategory=Vanilla LLM & RAG2025.1018.6
DirectBackbone=Qwen-2.5-7B, Category=Model Inference2025.1218.3
IRCoTBackbone=Qwen-2.5-3B, Category=Tool-integrated Methods2025.1216.4
DirectBackbone=Qwen-2.5-3B, Category=Model Inference2025.1214.9
IRCoTBackbone=Qwen-2.5-7B, Category=Tool-integrated Methods2025.1213.3