Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Reasoning on ARC Challenge (Capability)
Loading...
77.3
Capability
CSULoRA
67.8984
70.3392
72.78
75.2208
May 28, 2026
Capability
Updated 2d ago
Evaluation Results
Method
Method
Links
Capability
CSULoRA
Model=Gemma-3-4B-it
2026.05
77.3
Base model
Model=Gemma-3-4B-it
2026.05
77.13
SafeLoRA
Model=Gemma-3-4B-it
2026.05
77.13
SPLoRA
Model=Gemma-3-4B-it
2026.05
76.28
LoRA
Model=Gemma-3-4B-it
2026.05
76.11
SaLoRA
Model=Gemma-3-4B-it
2026.05
75.85
AlignGuard
Model=Gemma-3-4B-it
2026.05
75.77
LoRA
Model=Llama-3.2-3B-Ins...
2026.05
73.38
SafeLoRA
Model=Llama-3.2-3B-Ins...
2026.05
73.38
SPLoRA
Model=Llama-3.2-3B-Ins...
2026.05
73.29
CSULoRA
Model=Llama-3.2-3B-Ins...
2026.05
73.29
AlignGuard
Model=Llama-3.2-3B-Ins...
2026.05
72.78
SaLoRA
Model=Llama-3.2-3B-Ins...
2026.05
72.35
Base model
Model=Llama-3.2-3B-Ins...
2026.05
72.01
RESTA
Model=Llama-3.2-3B-Ins...
2026.05
71.16
RESTA
Model=Gemma-3-4B-it
2026.05
68.26
Feedback
Search any
task
Search any
task