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

Deductive Reasoning on ProofWriter (Pass@1, Variance)

97.4Pass@1

ADARFT

24.18443.19262.281.208Jun 10, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.06
97.4-
2025.06
970.2
2025.06
96.8-
2025.06
96.4-
2025.06
96.30.3
2025.06
95.6-
2025.06
95.6-
2025.06
94.8-
2025.06
93-
2025.06
92-
2025.06
91-
2025.06
90-
2025.06
89.2-
2025.06
88.8-
2025.06
88-
2025.06
88-
2025.06
87-
2025.06
27-