Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Expert Knowledge Q&A on GPQA
Loading...
42.86
Accuracy
Dense
26.844
31.002
35.16
39.318
Oct 7, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Dense
Model=Qwen-3 8B, Spars...
2025.10
42.86
Dense
Model=Qwen-3 14B, Spar...
2025.10
39.29
ARMOR
Model=Qwen-3 8B, Spars...
2025.10
33.93
SparseGPT
Model=Qwen-3 8B, Spars...
2025.10
32.14
ARMOR
Model=Qwen-3 14B, Spar...
2025.10
29.91
Wanda
Model=Qwen-3 8B, Spars...
2025.10
29.46
Wanda
Model=Qwen-3 14B, Spar...
2025.10
29.02
NoWag-P
Model=Qwen-3 8B, Spars...
2025.10
28.57
SparseGPT
Model=Qwen-3 14B, Spar...
2025.10
27.9
NoWag-P
Model=Qwen-3 14B, Spar...
2025.10
27.46
Feedback
Search any
task
Search any
task