Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Data Filtering on OpenWebText Quality
Loading...
88.2
Balanced Accuracy
GPT-4o
73.952
77.651
81.35
85.049
Oct 3, 2024
Balanced Accuracy
Human Preference
Updated 1mo ago
Evaluation Results
Method
Method
Links
Balanced Accuracy
Human Preference
GPT-4o
#Queries to GPT-4o=13....
2024.10
88.2
50
SIEVE
#Queries to GPT-4o=60K...
2024.10
86.3
53
GPT-3.5-Turbo
#Queries to GPT-4o=13....
2024.10
74.5
-
Feedback
Search any
task
Search any
task
