Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text Classification on HellaSwag
Loading...
78.9
Accuracy
GPT-3
42.188
51.719
61.25
70.781
Jul 14, 2021
Mar 20, 2022
Nov 25, 2022
Aug 1, 2023
Apr 7, 2024
Dec 12, 2024
Aug 19, 2025
Accuracy
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-3
# Params=175B, prompti...
2021.07
78.9
I-GLASS
Backbone=Mistral 7B, S...
2025.08
61.01
GRIFFIN
Backbone=Mistral 7B, S...
2025.08
60.97
GRIFFIN
Backbone=Gemma 7B, Spa...
2025.08
60.62
I-GLASS
Backbone=Gemma 7B, Spa...
2025.08
60.59
I-GLASS
Backbone=Llama2 7B, Sp...
2025.08
57.14
GRIFFIN
Backbone=Llama2 7B, Sp...
2025.08
57.14
I-GLASS
Backbone=ReLU-Llama2 7...
2025.08
53.95
GRIFFIN
Backbone=ReLU-Llama2 7...
2025.08
53.95
GPT-3 Large
# Params=760M, prompti...
2021.07
51
GRIFFIN
Backbone=OPT 6.7B, Spa...
2025.08
50.49
I-GLASS
Backbone=OPT 6.7B, Spa...
2025.08
50.45
HTLM-Manual
# Params=400M, prompti...
2021.07
47.9
GPT-3 Med
# Params=350M, prompti...
2021.07
43.6
Feedback
Search any
task
Search any
task