Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Commonsense Fact Verification on CREAK (test)
Loading...
88.6
Accuracy
RACO
49.288
59.494
69.7
79.906
May 10, 2023
Oct 2, 2023
Feb 24, 2024
Jul 18, 2024
Dec 10, 2024
May 4, 2025
Sep 26, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
RACO
#Total Params.=≥ 3B, S...
2023.05
88.6
DECKER
#Total Params.=~449M,...
2023.05
88.4
T5-3B
#Total Params.=~3B, Si...
2023.05
85.1
UNICORN
#Total Params.=~770M,...
2023.05
79.5
ICR
Backbone=Qwen2.5-7B
2025.09
79.2
Zero-shot
Backbone=Qwen2.5-7B
2025.09
77.8
GreaseLM
#Total Params.=~359M,...
2023.05
77.5
I2CL
Backbone=Qwen2.5-7B
2025.09
74.8
M²IV
Backbone=Qwen2.5-7B
2025.09
74.6
LIVE
Backbone=Qwen2.5-7B
2025.09
72.8
Few-shot*
Backbone=Qwen2.5-7B, F...
2025.09
59.7
ICR
Backbone=Llama2-7B
2025.09
56.4
M²IV
Backbone=Llama2-7B
2025.09
54
I2CL
Backbone=Llama2-7B
2025.09
52.6
Zero-shot
Backbone=Llama2-7B
2025.09
51.8
LIVE
Backbone=Llama2-7B
2025.09
51
Few-shot*
Backbone=Llama2-7B, Fe...
2025.09
50.8
Feedback
Search any
task
Search any
task