Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Open-Domain Question Answering on WebQuestions (WebQ) (dev)
Loading...
51.5
Exact Match
PAQ + FiE
26.124
32.712
39.3
45.888
Jun 9, 2021
Sep 4, 2021
Dec 1, 2021
Feb 27, 2022
May 26, 2022
Aug 22, 2022
Nov 18, 2022
Exact Match
Updated 4d ago
Evaluation Results
Method
Method
Links
Exact Match
PAQ + FiE
Model Scale=Base
2022.11
51.5
PAQ + FiE
Model Scale=Large
2022.11
50.1
EMDR2
top-K=50, # of params=...
2021.06
49.9
FiE
Model Scale=Large
2022.11
49.9
FiD (DPR retriever, T5 reader) (K=50)
top-K=50, # of params=...
2021.06
46
RAG-Sequence
top-K=50, # of params=...
2021.06
44.9
FiE
Model Scale=Base
2022.11
44.3
FiD (MSS + DPR retriever, T5 reader)
top-K=50, # of params=...
2021.06
43.5
GPT-3
top-K=0, # of params=175B
2021.06
41.5
FiD (DPR retriever, T5 reader) (K=1)
top-K=1, # of params=4...
2021.06
40.2
FiD (MSS retriever, MSS reader)
top-K=50, # of params=...
2021.06
39.1
ORQA
top-K=5, # of params=330M
2021.06
36.8
T5-XXL
top-K=0, # of params=11B
2021.06
35.6
FiD / T5-base (Ours)
top-K=0, # of params=2...
2021.06
31
T5-large
top-K=0, # of params=770M
2021.06
29.5
T5-base
top-K=0, # of params=220M
2021.06
28.2
BM25 + BERT
top-K=5, # of params=220M
2021.06
27.1
Feedback
Search any
task
Search any
task