Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-form Biography Generation on Bio FactScore
Loading...
81.2
FactScore
SELF-RAG
43.032
52.941
62.85
72.759
Oct 17, 2023
FactScore
Updated 4d ago
Evaluation Results
Method
Method
Links
FactScore
SELF-RAG
Scale=7B, Retrieval=Yes
2023.10
81.2
SELF-RAG
Scale=13B, Retrieval=Yes
2023.10
80.2
Ret-Llama2-Chat
Scale=13B, Retrieval=Y...
2023.10
79.9
Llama2-FT
Scale=7B, Retrieval=Ye...
2023.10
78.2
Llama2
Scale=7B, Retrieval=Yes
2023.10
78
Alpaca
Scale=13B, Retrieval=Yes
2023.10
77.7
Llama2
Scale=13B, Retrieval=Yes
2023.10
77.5
Alpaca
Scale=7B, Retrieval=Yes
2023.10
76.6
Ret-ChatGPT
Retrieval=Yes, Proprie...
2023.10
75.3
ChatGPT
Retrieval=No, Propriet...
2023.10
71.8
Perplexity.ai
Proprietary=true
2023.10
71.2
CoVE
Scale=65B, Mode=Iterat...
2023.10
71.2
Llama2-Chat
Scale=13B, Retrieval=N...
2023.10
55.9
Llama2
Scale=13B, Retrieval=No
2023.10
53.4
Alpaca
Scale=13B, Retrieval=No
2023.10
50.2
Alpaca
Scale=7B, Retrieval=No
2023.10
45.8
Llama2
Scale=7B, Retrieval=No
2023.10
44.5
Feedback
Search any
task
Search any
task