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

Multi-hop Question Answering on Musique

40.5EM

ARISE

Updated 2d ago

Evaluation Results

Method
ARISE 2025.04	40.5	65.87	-	-	-	-
Auto-RAG 2025.04	35.5	59.05	-	-	-	-
Auto-RAG 2025.04	29.5	57.19	-	-	-	-
RATT 2025.04	29.5	63.66	-	-	-	-
ARISE 2025.04	29	62.26	-	-	-	-
Self-Ask 2025.04	25	58.59	-	-	-	-
ARISE 2025.04	24.5	66.38	-	-	-	-
RATT 2025.04	24	63.76	-	-	-	-
StepSearch 2026.01	22.6	-	-	-	-	-
Agentic-R 2026.01	22.54	-	-	-	-	-
Dep-Search 2026.01	22.2	-	-	-	-	-
Query2Doc 2025.04	22	55.79	-	-	-	-
Verify-and-Edit 2025.04	22	55.3	-	-	-	-
Self-Ask 2025.04	22	57.48	-	-	-	-
CoT-SC 2025.04	22	59.43	-	-	-	-
Verify-and-Edit 2025.04	21.5	54.75	-	-	-	-
Auto-RAG 2025.04	21.5	52.61	-	-	-	-
MT-PPO 2026.01	21.5	-	-	-	-	-
E5 2026.01	21.39	-	-	-	-	-
Self-Ask 2025.04	20.5	52.14	-	-	-	-
HierSearch 2026.01	20.4	-	-	-	-	-
Agentic-R 2026.01	20.27	-	-	-	-	-
O2-Searcher 2026.01	20	-	-	-	-	-
Query2Doc 2025.04	19	49.91	-	-	-	-
REPLUG 2026.01	18.9	-	-	-	-	-
CoDA-Base 2025.12	18.7	-	-	-	-	-
R1-Searcher 2026.01	18.6	-	-	-	-	-
SCARLet 2026.01	18.53	-	-	-	-	-
ZeroSearch 2026.01	18.4	-	-	-	-	-
LLM-Embedder 2026.01	18.36	-	-	-	-	-
BGE 2026.01	18.36	-	-	-	-	-
REPLUG 2026.01	18.32	-	-	-	-	-
RATT 2025.04	18	56.58	-	-	-	-
E5 2026.01	17.74	-	-	-	-	-
StepSearch 2026.01	17.4	-	-	-	-	-
Search-R1 2026.01	17.4	-	-	-	-	-
LLM-Embedder 2026.01	17.33	-	-	-	-	-
Agentic-R 2026.01	17.29	-	-	-	-	-
AutoRefine-Base 2025.12	16.9	-	-	-	-	-
ZeroSearch 2026.01	16.8	-	-	-	-	-
SCARLet 2026.01	16.38	-	-	-	-	-
BGE 2026.01	16.21	-	-	-	-	-
CoT-SC 2025.04	16	57.46	-	-	-	-
REPLUG 2026.01	15.8	-	-	-	-	-
E5 2026.01	15.55	-	-	-	-	-
Self-Ask + Search Engine 2022.10	15.2	27.2	19.6	-	-	-
TSPO 2026.01	15.1	-	-	-	-	-
CoT-SC 2025.04	15	56.72	-	-	-	-
Search-R1 2026.01	14.6	-	-	-	-	-
Dep-Search 2026.01	14.6	-	-	-	-	-
Vanilla 2025.04	14.5	47.07	-	-	-	-
Query2Doc 2025.04	14.5	54.59	-	-	-	-
SCARLet 2026.01	14.39	-	-	-	-	-
BGE 2026.01	14.06	-	-	-	-	-
Vanilla 2025.04	14	47.07	-	-	-	-
LLM-Embedder 2026.01	13.9	-	-	-	-	-
Self-Ask 2022.10	13.8	27	16.2	-	-	-
Verify-and-Edit 2025.04	13.5	49.77	-	-	-	-
ReasonRAG 2026.01	12.8	-	-	-	-	-
Chain-of-Thought 2022.10	12.6	24.8	15.2	-	-	-
TSPO 2026.01	12.6	-	-	-	-	-
HierSearch 2026.01	12.4	-	-	-	-	-
Rejection Sampling 2026.01	12.3	-	-	-	-	-
O2-Searcher 2026.01	12	-	-	-	-	-
Vanilla 2025.04	11	47.07	-	-	-	-
RA-ISF 2026.01	10.6	-	-	-	-	-
Search-R1 2026.01	10.3	-	-	-	-	-
ZeroSearch 2026.01	9.8	-	-	-	-	-
IRCoT 2026.01	9.8	-	-	-	-	-
R1-Searcher 2026.01	9.4	-	-	-	-	-
ZeroSearch 2026.01	8.8	-	-	-	-	-
Search-O1 2026.01	8.6	-	-	-	-	-
Search-R1 2026.01	7.6	-	-	-	-	-
ReSearch-Base 2025.12	7.4	-	-	-	-	-
IRCoT 2026.01	7.2	-	-	-	-	-
R1-instruct 2026.01	7.2	-	-	-	-	-
RA-ISF 2026.01	7.2	-	-	-	-	-
ReasonRAG 2026.01	6.9	-	-	-	-	-
IRCoT 2026.01	6.7	-	-	-	-	-
IRCoT 2025.12	6.7	-	-	-	-	-
SFT 2026.01	6.6	-	-	-	-	-
Search-R1-Base 2025.12	6.6	-	-	-	-	-
Search Engine + LM postproc. 2022.10	6.5	16.1	8.5	-	-	-
IRCoT 2026.01	6.4	-	-	-	-	-
R1-instruct 2026.01	6	-	-	-	-	-
R1-Instruct 2025.12	6	-	-	-	-	-
Rejection Sampling 2026.01	5.9	-	-	-	-	-
Search-o1 2026.01	5.8	-	-	-	-	-
RAG 2026.01	5.8	-	-	-	-	-
Direct Prompting 2022.10	5.6	16.1	6.9	-	-	-
Vanilla RAG 2026.01	5.6	-	-	-	-	-
R1-Base 2025.12	5.5	-	-	-	-	-
Search-o1 2026.01	5.4	-	-	-	-	-
Search-o1 2025.12	5.4	-	-	-	-	-
Search-O1 2026.01	5.2	-	-	-	-	-
Directly Inference 2026.01	4.8	-	-	-	-	-
RAG 2026.01	4.7	-	-	-	-	-
Naive RAG 2025.12	4.7	-	-	-	-	-
SFT 2026.01	4.4	-	-	-	-	-
Directly Inference 2026.01	4.4	-	-	-	-	-

Showing 100 of 213 rows