Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Logic Reasoning on Zebra riddles (test)
Loading...
98.7
Accuracy
Glauber-UL2 (N=3)
76.028
81.914
87.8
93.686
May 5, 2026
Accuracy
Updated 27d ago
Evaluation Results
Method
Method
Links
Accuracy
Glauber-UL2 (N=3)
Params=21M
2026.05
98.7
MDLM (Top-K Prob.)
Params=19M
2026.05
98.5
MDLM (Top-K Margin)
Params=19M
2026.05
98.3
Glauber-UL2 (N=1)
Params=21M
2026.05
94.1
AR (w/ ordering)
Params=42M
2026.05
91.2
AR (w/o ordering)
Params=42M
2026.05
80.3
MDLM (vanilla)
Params=19M
2026.05
76.9
Feedback
Search any
task
Search any
task