Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Zero-shot Downstream Tasks on ARC-C, ARC-E, HellaSwag, PIQA, and WinoGrande
Loading...
74.35
Downstream Average
FP16
35.3292
45.4596
55.59
65.7204
Jun 1, 2026
Downstream Average
Updated 1mo ago
Evaluation Results
Method
Method
Links
Downstream Average
FP16
Model=LLaMA-3.1-8B, Se...
2026.06
74.35
FP16
Model=LLaMA-2-7B, Sett...
2026.06
68.66
SYM-INT
Model=LLaMA-2-7B, Sett...
2026.06
62
Qift-MNZ
Model=LLaMA-2-7B, Sett...
2026.06
61.57
SYM-INT
Model=LLaMA-3.1-8B, Se...
2026.06
59.72
Qift-MNZ
Model=LLaMA-3.1-8B, Se...
2026.06
56.09
Qift-MNZ
Model=LLaMA-2-7B, Sett...
2026.06
47.94
SYM-INT
Model=LLaMA-2-7B, Sett...
2026.06
42.11
Qift-MNZ
Model=LLaMA-3.1-8B, Se...
2026.06
40.64
SYM-INT
Model=LLaMA-3.1-8B, Se...
2026.06
36.83
Feedback
Search any
task
Search any
task
