Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Automated Program Repair on 10 projects (100 total issues)
Loading...
70
Total Solved Issues
AIR
26.32
37.66
49
60.34
Dec 9, 2025
Total Solved Issues
Success Rate
Mean Solved per Project
Median Solved per Project
Std Dev Solved per Project
Min Solved per Project
Max Solved per Project
Updated 3mo ago
Evaluation Results
Method
Method
Links
Total Solved Issues
Success Rate
Mean Solved per Project
Median Solved per Project
Std Dev Solved per Project
Min Solved per Project
Max Solved per Project
AIR
2025.12
70
0.7
7
8
2.05
4
9
Gemini-2.5 pro
2025.12
41
0.41
4.1
3.5
2.56
0
8
Claude 4 Sonnet
2025.12
28
0.28
2.8
2.5
1.93
0
6
Feedback
Search any
task
Search any
task