Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Zero-shot Evaluation on 0-shot
Loading...
71.75
Accuracy
Dense
35.1628
44.6614
54.16
63.6586
May 11, 2026
Accuracy
Updated 21d ago
Evaluation Results
Method
Method
Links
Accuracy
Dense
Model=14B-Base
2026.05
71.75
Dense
Model=32B
2026.05
71.49
ADMM-Q
Model=14B-Base, Weight...
2026.05
71.07
GPTQ
Model=14B-Base, Weight...
2026.05
70.76
AWQ
Model=14B-Base, Weight...
2026.05
69.82
Dense
Model=8B-Base
2026.05
69.07
Dense
Model=4B-Base
2026.05
66.72
Dense
Model=1.7B-Base
2026.05
62.54
AWQ
Model=1.7B-Base, Weigh...
2026.05
60.19
ADMM-Q
Model=1.7B-Base, Weigh...
2026.05
58.34
ADMM-Q
Model=8B-Base, Weight...
2026.05
57.8
GPTQ
Model=1.7B-Base, Weigh...
2026.05
56.58
ADMM-Q
Model=32B, Weight Bits=W2
2026.05
55.65
GPTQ
Model=8B-Base, Weight...
2026.05
54.43
GPTQ
Model=32B, Weight Bits=W2
2026.05
52.77
AWQ
Model=8B-Base, Weight...
2026.05
51.08
AWQ
Model=32B, Weight Bits=W2
2026.05
36.57
Feedback
Search any
task
Search any
task