Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-hop Text QA on HotpotQA 1% v1.1 (train)
Loading...
63.1
F1
ReasonBERT_R
38.868
45.159
51.45
57.741
Sep 10, 2021
F1
EM
Updated 4d ago
Evaluation Results
Method
Method
Links
F1
EM
ReasonBERT_R
Backbone=RoBERTa-base
2021.09
63.1
50.2
ReasonBERT_B
Backbone=BERT-base
2021.09
57.6
45.3
Splinter
Backbone=Splinter-base
2021.09
57
44.2
SpanBERT
Backbone=SpanBERT-base
2021.09
56.5
44.1
RoBERTa
Backbone=RoBERTa-base
2021.09
56
43.1
SSPT
Backbone=SSPT-base
2021.09
54.7
41.8
BERT
Backbone=BERT-base
2021.09
39.8
28.6
Feedback
Search any
task
Search any
task