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

Formal Theorem Proving on miniF2F Isabelle (test)

51.2Success Rate

Lyra

8.76819.78430.841.816Oct 21, 2022Dec 17, 2022Feb 13, 2023Apr 11, 2023Jun 8, 2023Aug 4, 2023Oct 1, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.09
51.2
2023.10
50
2023.10
50
2023.09
47.9
2023.09
47.1
2023.05
45.5
2023.10
45.5
2023.10
45.5
2023.09
45.5
2023.05
44.3
2023.09
44.2
2023.05
40.6
2022.10
39.3
2023.10
39.3
2023.09
39.3
2022.10
38.9
2023.05
38.9
2023.09
38.9
2023.05
38.5
2022.10
37.7
2022.10
36.5
2022.10
35.3
2022.10
35.3
2022.10
35.2
2023.05
35.2
2023.10
35.2
2023.09
35.2
2022.10
34
2022.10
30.3
2022.10
29.9
2023.05
29.9
2023.10
29.9
2023.09
29.9
2022.10
20.9
2023.05
20.9
2023.09
20.9
2022.10
10.4
2023.05
10.4
2023.09
10.4