Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Common Sense Reasoning on Six Benchmarks Suite (ARC-e, PIQA, OpenbookQA, Winogrande, HellaSwag, MathQA)
Loading...
61
Average Accuracy
Original
30.84
38.67
46.5
54.33
Apr 2, 2026
Average Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Average Accuracy
Original
Model=MISTRAL-7B, Comp...
2026.04
61
Original
Model=LLAMA 2-7B, Comp...
2026.04
57
Swift-SVD
Model=LLAMA 2-7B, Comp...
2026.04
56
Swift-SVD*
Model=LLAMA 2-7B, Comp...
2026.04
56
Swift-SVD*
Model=MISTRAL-7B, Comp...
2026.04
55
Swift-SVD
Model=MISTRAL-7B, Comp...
2026.04
54
SVD-LLM (W)
Model=LLAMA 2-7B, Comp...
2026.04
53
Original
Model=OPT-6.7B, Compre...
2026.04
52
Swift-SVD*
Model=OPT-6.7B, Compre...
2026.04
51
Swift-SVD
Model=OPT-6.7B, Compre...
2026.04
50
SVD-LLM (W)
Model=MISTRAL-7B, Comp...
2026.04
42
SVD-LLM (W)
Model=OPT-6.7B, Compre...
2026.04
41
ASVD
Model=LLAMA 2-7B, Comp...
2026.04
36
ASVD
Model=OPT-6.7B, Compre...
2026.04
32
ASVD
Model=MISTRAL-7B, Comp...
2026.04
32
Feedback
Search any
task
Search any
task