Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Pair-wise comparison on JudgeBench

75.7Accuracy

CCE@16

57.60462.3026771.698Feb 18, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.02
75.7
2025.02
70.6
2025.02
70.4
2025.02
69.7
2025.02
68.9
2025.02
68.9
2025.02
68.6
2025.02
68.3
2025.02
67.2
2025.02
67.1
2025.02
66.6
2025.02
66.3
2025.02
64
2025.02
63.5
2025.02
62.9
2025.02
58.3