Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multiple-choice tasks on Natural Questions
Loading...
59.6
Accuracy
TruthX
54.712
55.981
57.25
58.519
Feb 27, 2024
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
TruthX
Backbone=Llama-2-7B-Chat
2024.02
59.6
ITI
Backbone=Llama-2-7B-Chat
2024.02
57.83
Llama-2-7B-Chat
Backbone=Llama-2-7B-Chat
2024.02
54.9
Feedback
Search any
task
Search any
task