Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Debugging on LiveCodeBench February-May 2025 (evaluation window)
Loading...
36.6
Accuracy
MGDebugger
28.696
30.748
32.8
34.852
Oct 2, 2024
Accuracy
RSR (%)
Updated 3mo ago
Evaluation Results
Method
Method
Links
Accuracy
RSR (%)
MGDebugger
Model=GPT-4o
2024.10
36.6
10.8
Reflexion
Model=GPT-4o
2024.10
33.6
5.4
Self-Debugging (Expl.)
Model=GPT-4o
2024.10
32.8
4.3
No-Debugging
Model=GPT-4o
2024.10
29
-
Feedback
Search any
task
Search any
task