Share your thoughts, 1 month free Claude Pro on usSee more

Mathematics Problem Solving on MATH500 (test)

61.2Exact Match Accuracy

Top-k

Updated 4d ago

Evaluation Results

Method	Links
Top-k 2026.04		61.2
Min-k 2026.04		61.2
Min-k 2026.04		61
Top-nσ 2026.04		60.6
Min-k 2026.04		60
Min-k 2026.04		60
Min-p 2026.04		59.8
Min-k 2026.04		59.8
Top-p 2026.04		59.4
Min-k 2026.04		59.4
Min-p 2026.04		59.2
Top-nσ 2026.04		59.2
Top-nσ 2026.04		59
Top-k 2026.04		58.8
Top-nσ 2026.04		58.8
Top-p 2026.04		58
Top-nσ 2026.04		58
Top-nσ 2026.04		57.8
Min-p 2026.04		57
Top-k 2026.04		53.4
Top-p 2026.04		53
Min-p 2026.04		49
Min-k 2026.04		46.4
Min-k 2026.04		46.4
Top-k 2026.04		44.4
Top-p 2026.04		44.2
Top-k 2026.04		44
Min-p 2026.04		43.8
Min-k 2026.04		43.6
Top-nσ 2026.04		43.4
Top-nσ 2026.04		43.4
Top-nσ 2026.04		43.2
Min-k 2026.04		43.2
Min-k 2026.04		43
Top-nσ 2026.04		42.4
Top-nσ 2026.04		42.2
Top-nσ 2026.04		41.8
Min-k 2026.04		41.4
Min-p 2026.04		40.6
Top-p 2026.04		36.8
Top-k 2026.04		35.6
Top-p 2026.04		29.8
Min-p 2026.04		29.4
Top-k 2026.04		21.4
Top-k 2026.04		15.8
Top-p 2026.04		12.2
Min-p 2026.04		12.2
Min-p 2026.04		10.2
Top-k 2026.04		3.4
Top-p 2026.04		2.4
Top-k 2026.04		1.4
Min-p 2026.04		1.4
Top-p 2026.04		0.6
Top-k 2026.04		0
Top-p 2026.04		0
Top-p 2026.04		0
Min-p 2026.04		0
Top-k 2026.04		0
Top-p 2026.04		0
Min-p 2026.04		0