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

Code Evaluation on BigCodeBench

82.02Accuracy

GPT-o1-preview

41.241651.828362.41573.0017Feb 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
82.02
2025.02
79.12
2025.02
77.37
2025.02
75.7
2025.02
72.37
2025.02
71.84
2025.02
71.23
2025.02
70.7
2025.02
70.44
2025.02
68.77
2025.02
63.86
2025.02
63.33
2025.02
63.33
2025.02
62.46
2025.02
57.89
2025.02
52.45
2025.02
51.93
2025.02
51.75
2025.02
50.96
2025.02
49.04
2025.02
45.88
2025.02
43.16
2025.02
42.81