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

Detective Puzzle Reasoning on DP Medium

83.2SA

SABA

33.69646.54859.472.252Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
83.274.973.592.2
2026.04
7779.972.187.9
2026.04
76.366.572.288
2026.04
75.168.469.986.9
2026.04
73.665.668.587.6
2026.04
72.268.864.982.9
2026.04
70.364.666.479.9
2026.04
65.566.76576.4
2026.04
6456.462.175.5
2026.04
61.855.759.872.7
2026.04
59.951.863.169.8
2026.04
58.664.96272.2
2026.04
52.548.252.367.9
2026.04
51.245.14558.7
2026.04
48.164.35862.5
2026.04
38.548.24442.4
2026.04
3845.94848.1
2026.04
35.644.545.335.1