Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Zero-shot Commonsense Reasoning on Zero-shot tasks (test)
Loading...
61
Average Accuracy
Original
41.24
46.37
51.5
56.63
Feb 16, 2026
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
Original
Model=Llama-30B
2026.02
61
SVD-LLM v2
Model=Llama-30B, Statu...
2026.02
60
COMPOT
Model=Llama-30B
2026.02
60
Original
Model=Llama-13B
2026.02
59
COMPOT
Model=Llama-13B
2026.02
57
SVD-LLM
Model=Llama-30B
2026.02
57
SVD-LLM v2
Model=Llama-13B, Statu...
2026.02
56
SVD-LLM
Model=Llama-13B
2026.02
55
ASVD
Model=Llama-13B
2026.02
54
ASVD
Model=Llama-30B
2026.02
44
FWSVD
Model=Llama-13B
2026.02
43
FWSVD
Model=Llama-30B
2026.02
42
Feedback
Search any
task
Search any
task
