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

Code Correctness Evaluation on APPS

80Accuracy

MCTS-Judge

39.4449.9760.571.03Oct 4, 2024Oct 26, 2024Nov 18, 2024Dec 11, 2024Jan 3, 2025Jan 26, 2025Feb 18, 2025
Updated 6d ago

Evaluation Results

MethodLinks
2025.02
80-
2025.02
80-
2025.02
79-
2025.02
78-
2025.02
78-
2025.02
76-
2025.02
75-
2025.02
75-
2025.02
72-
2025.02
72-
2025.02
72-
2025.02
68-
2025.02
65-
2025.02
65-
2025.02
62-
2025.02
62-
2025.02
62-
2025.02
62-
2025.02
60-
2025.02
60-
2025.02
56-
2025.02
56-
2025.02
55-
2025.02
54-
2024.10
53.218.6
2024.10
53.261.1
2025.02
53-
2024.10
52.560.1
2024.10
51.413.4
2024.10
51.215.5
2024.10
51.266.7
2024.10
51.217.5
2024.10
51.253.7
2024.10
51.118.9
2024.10
50.95.5
2024.10
50.911
2024.10
50.642.8
2024.10
50.56.7
2024.10
50.512.6
2024.10
50.264.8
2024.10
5044
2024.10
503.4
2024.10
49.61.4
2024.10
49.561.1
2024.10
49.113.9
2024.10
49.128.6
2024.10
48.26.5
2024.10
4852.8
2025.02
48-
2024.10
47.914.6
2024.10
47.526.9
2025.02
42-
2025.02
41-