Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Data Contamination Detection on Omni-MATH (Dataset U)
Loading...
15.85
Reference Score (S)
ZCP
-0.44472
3.78564
8.016
12.24636
May 21, 2026
Reference Score (S)
Score (S)
Contamination Score (C)
Updated 12d ago
Evaluation Results
Method
Method
Links
Reference Score (S)
Score (S)
Contamination Score (C)
ZCP
Model=FT Qwen-Math, Me...
2026.05
15.85
17.13
63.6
ZCP
Model=FT Qwen-Math, Me...
2026.05
12.3
13.81
55.1
ZCP
Model=FT Qwen-Math, Me...
2026.05
0.359
0.375
61.8
ZCP
Model=FT Qwen-Math, Me...
2026.05
0.182
0.194
59.1
Feedback
Search any
task
Search any
task
