Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Snarks detection on Snarks (test)
Loading...
91.6
Accuracy
AMPLIFY
48.336
59.568
70.8
82.032
May 19, 2023
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
AMPLIFY
Model=GPT-3.5, Prompti...
2023.05
91.6
AMPLIFY
Model=GPT-3, Prompting...
2023.05
80.5
Human-Rater
Model=Human, Prompting...
2023.05
76.7
GPT-3.5
Model=GPT-3.5, Prompti...
2023.05
75
SOTA
Model=N/A, Prompting S...
2023.05
71.3
GPT-3.5
Model=GPT-3.5, Prompti...
2023.05
69.4
GPT-3
Model=GPT-3, Prompting...
2023.05
61.1
GPT-3
Model=GPT-3, Prompting...
2023.05
52.7
Random
Model=N/A, Prompting S...
2023.05
50
Feedback
Search any
task
Search any
task
