Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math on Real-data Math Gemini outputs (3% verified data)
Loading...
66.35
Original Accuracy
Logistic Regression
63.0325
64.69125
66.35
68.00875
Jun 18, 2026
Original Accuracy
Adjusted Accuracy
Accuracy Gain
Human Verification Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Original Accuracy
Adjusted Accuracy
Accuracy Gain
Human Verification Rate
Logistic Regression
Question Type=Math, Da...
2026.06
66.35
59.71
-6.64
83
Multilayer Perceptron
Question Type=Math, Da...
2026.06
66.35
59.86
-6.5
83
Random Forest
Question Type=Math, Da...
2026.06
66.35
65.63
-0.72
83
Label Propagation
Question Type=Math, Da...
2026.06
66.35
56.17
-10.19
83
nnPU
Question Type=Math, Da...
2026.06
66.35
66.19
-0.16
83
AURA
Question Type=Math, Da...
2026.06
66.35
68.79
2.43
96.2
Feedback
Search any
task
Search any
task