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

General Reasoning on ZebraLogic (Accuracy (%))

96.3Accuracy (%)

TeamTR (Heterogeneous)

17.05237.62658.278.774Apr 17, 2026Apr 19, 2026Apr 21, 2026Apr 24, 2026Apr 26, 2026Apr 28, 2026May 1, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
96.3
2026.05
94.7
2026.04
93.1
2026.04
89.5
2026.05
89.5
88.9
2026.05
88.9
2026.04
88.8
2026.05
88.8
2026.04
86.3
2026.05
86.3
2026.04
85.1
2026.05
85.1
2026.04
84.1
2026.05
84.1
2026.04
80.7
2026.04
76.8
2026.05
76.8
71.3
2026.05
71.3
2026.04
36.7
2026.05
36.7
2026.04
35.4
2026.05
35.4
2026.04
33.1
2026.04
29.2
2026.04
26.6
20.1
2026.05
20.1