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

Theorem Proving on miniF2F Lean (test)

52Pass@64

DeepSeekMath-Base

7.2818.8930.542.11May 23, 2022Sep 21, 2022Jan 21, 2023May 23, 2023Sep 22, 2023Jan 22, 2024May 23, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.05
52-
2024.05
50-
2024.05
48.8-
2024.05
46.3-
2024.05
46.3-
2022.05
41-
2024.05
41-
2022.05
40.6-
2022.05
38.9-
2022.05
36.6-
2024.05
36.6-
2022.05
35.3-
2024.05
34.5-
2024.05
30-
2024.05
29.6-
2024.05
29.2-
2024.05
27.5-
2024.05
26.6-
2024.05
26.2-
2024.05
25.8-
2024.05
25-
2024.05
24.6-
2024.05
23-
2024.05
9-