Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Natural Language Processing
/
Question Answering
/
HotpotQA
Question Answering on HotpotQA
Metric: SUP-F1 (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
SUP-F1 (best first)
SUP-F1 (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
SUP-F1
▼
Extra Data
Paper
Date
↕
Code
1
Beam Retrieval
0.901
No
End-to-End Beam Retrieval for Multi-Hop Question...
2023-08-17
Code
2
BigBird-etc
0.891
No
Big Bird: Transformers for Longer Sequences
2020-07-28
Code
3
AISO
0.86
No
Adaptive Information Seeking for Open-Domain Que...
2021-09-14
Code
4
Chain-of-Skills
0.853
No
Chain-of-Skills: A Configurable Model for Open-d...
2023-05-04
Code
5
TPRR
0.843
No
-
-
-
6
EBS-Large
0.84
No
-
-
-
7
HopRetriever + Sp-search
0.835
No
HopRetriever: Retrieve Hops over Wikipedia to An...
2020-12-31
-
8
IRRR+
0.832
No
Answering Open-Domain Questions of Varying Reaso...
2020-10-23
Code
9
EBS-SH
0.831
No
-
-
-
10
HopRetriever
0.826
No
-
-
-
11
IRRR
0.821
No
Answering Open-Domain Questions of Varying Reaso...
2020-10-23
Code
12
HopRetriever-V2
0.818
No
-
-
-
13
AFSGraph-retriever
0.812
No
-
-
-
14
Recursive Dense Retriever
0.809
No
Answering Complex Open-Domain Questions with Mul...
2020-09-27
Code
15
Step-by-Step Retriever
0.8
No
-
-
-
16
HopRetriever-V1
0.793
No
-
-
-
17
DDRQA
0.789
No
Answering Any-hop Open-domain Questions with Ite...
2020-09-16
-
18
DR model large
0.778
No
-
-
-
19
HGN-albert + SemanticRetrievalMRS IR
0.774
No
-
-
-
20
Model name
0.772
No
-
-
-
21
HopAns
0.772
No
-
-
-
22
Multi-dimensional-AFSGraph
0.772
No
-
-
-
23
Anonymous
0.771
No
-
-
-
24
AFSgraph
0.769
No
-
-
-
25
Tree-shaped-cluster
0.768
No
-
-
-
26
HGN-large + SemanticRetrievalMRS IR
0.768
No
-
-
-
27
Robustly Fine-tuned Graph-based Recurrent Retriever
0.764
No
Learning to Retrieve Reasoning Paths over Wikipe...
2019-11-24
Code
28
HGN + SemanticRetrievalMRS IR
0.764
No
Hierarchical Graph Network for Multi-hop Questio...
2019-11-09
Code
29
AFSgraph model
0.759
No
-
-
-
30
SAFSR model
0.757
No
HotpotQA: A Dataset for Diverse, Explainable Mul...
2018-09-25
Code
31
RoBERTa-DenseRetriever-Fast
0.749
No
-
-
-
32
DPR-recurrent
0.749
No
-
-
-
33
RoBERTa-DenseRetriever
0.748
No
-
-
-
34
GAR-BERT
0.747
No
-
-
-
35
GAR
0.739
No
-
-
-
36
Quark + SemanticRetrievalMRS IR
0.73
No
A Simple Yet Strong Pipeline for HotpotQA
2020-04-14
-
37
Graph-based Recurrent Retriever
0.73
No
-
-
-
38
DR model
0.725
No
-
-
-
39
MIR+EPS+BERT
0.72
No
-
-
-
40
Transformer-XH-final
0.714
No
-
-
Code
41
GraphRR-Fast
0.713
No
-
-
-
42
SemanticRetrievalMRS
0.708
No
Revealing the Importance of Semantic Retrieval f...
2019-09-17
Code
43
Transformer-XH
0.7
No
-
-
-
44
GoldEn Retriever
0.642
No
Answering Complex Open-domain Questions Through ...
2019-10-15
Code
45
DrKIT
0.598
No
-
-
-
46
PR-Bert
0.596
No
-
-
-
47
SAFSr-Bert
0.585
No
-
-
-
48
Cognitive Graph QA
0.577
No
Cognitive Graph for Multi-Hop Reading Comprehens...
2019-05-14
Code
49
Entity-centric BERT Pipeline
0.573
No
-
-
-
50
IKFGraph
0.512
No
-
-
-
51
GRN + BERT
0.497
No
-
-
-
52
HGN Model-reproduce
0.493
No
-
-
-
53
GRN
0.488
No
-
-
-
54
MUPPET
0.473
No
Multi-Hop Paragraph Retrieval for Open-Domain Qu...
2019-06-15
Code
55
KGNN
0.472
No
Multi-Paragraph Reasoning with Knowledge-enhance...
2019-11-06
-
56
SAQA
0.472
No
-
-
-
57
AnonymousQ
0.468
No
-
-
-
58
GAR-NOSF
0.448
No
-
-
-
59
QFE
0.444
No
Answering while Summarizing: Multi-task Learning...
2019-05-21
-
60
Entity-centric IR
0.432
No
-
-
-
61
SAFSr_model
0.406
No
-
-
-
62
SuppBERT
0.4
No
-
-
-
63
Baseline Model
0.377
No
HotpotQA: A Dataset for Diverse, Explainable Mul...
2018-09-25
Code
64
tes
0.078
No
-
-
-
65
PromptRank-fewshot-2-demo
0
No
-
-
-
66
graph-recurrent-retriever+roberta-base w. S/R-pretraining
0
No
-
-
-
67
TPReasoner w/o BERT
0
No
-
-
-
68
MultiQA
0
No
-
-
-
69
DecompRC
0
No
-
-
Code
70
0
No
-
-
-
71
Mistral multi hop with very large sources
0
No
-
-
-
#1
Beam Retrieval
SOTA
0.901
SUP-F1
· 2023-08-17
End-to-End Beam Retrieval for Multi-Hop Question Answering
Code
#2
BigBird-etc
SOTA
0.891
SUP-F1
· 2020-07-28
Big Bird: Transformers for Longer Sequences
Code
#3
AISO
0.86
SUP-F1
· 2021-09-14
Adaptive Information Seeking for Open-Domain Question Answering
Code
#4
Chain-of-Skills
0.853
SUP-F1
· 2023-05-04
Chain-of-Skills: A Configurable Model for Open-domain Question Answering
Code
#5
TPRR
0.843
SUP-F1
No paper
#6
EBS-Large
0.84
SUP-F1
No paper
#7
HopRetriever + Sp-search
0.835
SUP-F1
· 2020-12-31
HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions
#8
IRRR+
0.832
SUP-F1
· 2020-10-23
Answering Open-Domain Questions of Varying Reasoning Steps from Text
Code
#9
EBS-SH
0.831
SUP-F1
No paper
#10
HopRetriever
0.826
SUP-F1
No paper
#11
IRRR
0.821
SUP-F1
· 2020-10-23
Answering Open-Domain Questions of Varying Reasoning Steps from Text
Code
#12
HopRetriever-V2
0.818
SUP-F1
No paper
#13
AFSGraph-retriever
0.812
SUP-F1
No paper
#14
Recursive Dense Retriever
0.809
SUP-F1
· 2020-09-27
Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
Code
#15
Step-by-Step Retriever
0.8
SUP-F1
No paper
#16
HopRetriever-V1
0.793
SUP-F1
No paper
#17
DDRQA
0.789
SUP-F1
· 2020-09-16
Answering Any-hop Open-domain Questions with Iterative Document Reranking
#18
DR model large
0.778
SUP-F1
No paper
#19
HGN-albert + SemanticRetrievalMRS IR
0.774
SUP-F1
No paper
#20
Model name
0.772
SUP-F1
No paper
#21
HopAns
0.772
SUP-F1
No paper
#22
Multi-dimensional-AFSGraph
0.772
SUP-F1
No paper
#23
Anonymous
0.771
SUP-F1
No paper
#24
AFSgraph
0.769
SUP-F1
No paper
#25
Tree-shaped-cluster
0.768
SUP-F1
No paper
#26
HGN-large + SemanticRetrievalMRS IR
0.768
SUP-F1
No paper
#27
Robustly Fine-tuned Graph-based Recurrent Retriever
0.764
SUP-F1
· 2019-11-24
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
Code
#28
HGN + SemanticRetrievalMRS IR
SOTA
0.764
SUP-F1
· 2019-11-09
Hierarchical Graph Network for Multi-hop Question Answering
Code
#29
AFSgraph model
0.759
SUP-F1
No paper
#30
SAFSR model
SOTA
0.757
SUP-F1
· 2018-09-25
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Code
#31
RoBERTa-DenseRetriever-Fast
0.749
SUP-F1
No paper
#32
DPR-recurrent
0.749
SUP-F1
No paper
#33
RoBERTa-DenseRetriever
0.748
SUP-F1
No paper
#34
GAR-BERT
0.747
SUP-F1
No paper
#35
GAR
0.739
SUP-F1
No paper
#36
Quark + SemanticRetrievalMRS IR
0.73
SUP-F1
· 2020-04-14
A Simple Yet Strong Pipeline for HotpotQA
#37
Graph-based Recurrent Retriever
0.73
SUP-F1
No paper
#38
DR model
0.725
SUP-F1
No paper
#39
MIR+EPS+BERT
0.72
SUP-F1
No paper
#40
Transformer-XH-final
0.714
SUP-F1
No paper
Code
#41
GraphRR-Fast
0.713
SUP-F1
No paper
#42
SemanticRetrievalMRS
0.708
SUP-F1
· 2019-09-17
Revealing the Importance of Semantic Retrieval for Machine Reading at Scale
Code
#43
Transformer-XH
0.7
SUP-F1
No paper
#44
GoldEn Retriever
0.642
SUP-F1
· 2019-10-15
Answering Complex Open-domain Questions Through Iterative Query Generation
Code
#45
DrKIT
0.598
SUP-F1
No paper
#46
PR-Bert
0.596
SUP-F1
No paper
#47
SAFSr-Bert
0.585
SUP-F1
No paper
#48
Cognitive Graph QA
0.577
SUP-F1
· 2019-05-14
Cognitive Graph for Multi-Hop Reading Comprehension at Scale
Code
#49
Entity-centric BERT Pipeline
0.573
SUP-F1
No paper
#50
IKFGraph
0.512
SUP-F1
No paper
#51
GRN + BERT
0.497
SUP-F1
No paper
#52
HGN Model-reproduce
0.493
SUP-F1
No paper
#53
GRN
0.488
SUP-F1
No paper
#54
MUPPET
0.473
SUP-F1
· 2019-06-15
Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
Code
#55
KGNN
0.472
SUP-F1
· 2019-11-06
Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
#56
SAQA
0.472
SUP-F1
No paper
#57
AnonymousQ
0.468
SUP-F1
No paper
#58
GAR-NOSF
0.448
SUP-F1
No paper
#59
QFE
0.444
SUP-F1
· 2019-05-21
Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
#60
Entity-centric IR
0.432
SUP-F1
No paper
#61
SAFSr_model
0.406
SUP-F1
No paper
#62
SuppBERT
0.4
SUP-F1
No paper
#63
Baseline Model
0.377
SUP-F1
· 2018-09-25
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Code
#64
tes
0.078
SUP-F1
No paper
#65
PromptRank-fewshot-2-demo
0
SUP-F1
No paper
#66
graph-recurrent-retriever+roberta-base w. S/R-pretraining
0
SUP-F1
No paper
#67
TPReasoner w/o BERT
0
SUP-F1
No paper
#68
MultiQA
0
SUP-F1
No paper
#69
DecompRC
0
SUP-F1
No paper
Code
#70
0
SUP-F1
No paper
#71
Mistral multi hop with very large sources
0
SUP-F1
No paper