Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on ARC Challenge (Accuracy and Sample Size)
Loading...
90.3
Accuracy
GrACE-SC
85.724
86.912
88.1
89.288
Sep 11, 2025
Accuracy
Sample Size
Updated 11d ago
Evaluation Results
Method
Method
Links
Accuracy
Sample Size
GrACE-SC
Backbone=Qwen2.5, Samp...
2025.09
90.3
8
GrACE-ES
Backbone=Qwen2.5, Samp...
2025.09
90.1
2.47
SC
Backbone=Qwen2.5, Samp...
2025.09
89.5
8
ESC
Backbone=Qwen2.5, Samp...
2025.09
89.3
4.32
ASC
Backbone=Qwen2.5, Samp...
2025.09
88.7
2.23
GrACE-SC
Backbone=Llama-3.1, Sa...
2025.09
87.2
8
GrACE-ES
Backbone=Llama-3.1, Sa...
2025.09
87.2
2.14
SC
Backbone=Llama-3.1, Sa...
2025.09
86.3
8
ESC
Backbone=Llama-3.1, Sa...
2025.09
86.3
4.69
ASC
Backbone=Llama-3.1, Sa...
2025.09
85.9
2.34
Feedback
Search any
task
Search any
task