Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Answering on NQ DPR 3610 questions
Loading...
50
EM
RankRAG
26.704
32.752
38.8
44.848
Jul 2, 2024
EM
Updated 4d ago
Evaluation Results
Method
Method
Links
EM
RankRAG
Backbone=Llama-3, Mode...
2024.07
50
RankRAG
Backbone=Llama-2, Mode...
2024.07
48.7
RankRAG
Backbone=Llama-2, Mode...
2024.07
46.2
RankRAG
Backbone=Llama-3, Mode...
2024.07
46.1
ChatQA-1.5
Backbone=Llama-3, Mode...
2024.07
46
ChatQA-1.0
Backbone=Llama-2, Mode...
2024.07
45
ChatQA-1.5
Backbone=Llama-3, Mode...
2024.07
44.1
ChatQA-1.0
Backbone=Llama-2, Mode...
2024.07
43.9
RankRAG
Backbone=Llama-2, Mode...
2024.07
42.4
GPT-3.5-0613 RAG
Model Family=OpenAI GP...
2024.07
42.3
GPT-4-turbo-2024-0409
Model Family=OpenAI GPT
2024.07
38.3
Llama-2-Chat
Backbone=Llama-2, Conf...
2024.07
37.7
Llama-3-Instruct
Backbone=Llama-3, Mode...
2024.07
37.3
GPT-4-0613
Model Family=OpenAI GPT
2024.07
37.2
ChatQA-1.0
Backbone=Llama-2, Mode...
2024.07
37
GPT-4-turbo-2024-0409 RAG
Model Family=OpenAI GP...
2024.07
36.3
GPT-4-0613 RAG
Model Family=OpenAI GP...
2024.07
36.2
GPT-3.5-0613
Model Family=OpenAI GPT
2024.07
35.2
Llama-3-Instruct
Backbone=Llama-3, Mode...
2024.07
27.6
Feedback
Search any
task
Search any
task