Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Issue Resolution on SWE-bench Lite
Loading...
31.4
Overall Resolution Success
CADMAS-CTX
21.936
24.393
26.85
29.307
Apr 20, 2026
Overall Resolution Success
Isolated Accuracy
Chained Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall Resolution Success
Isolated Accuracy
Chained Accuracy
CADMAS-CTX
2026.04
31.4
33.5
24.8
Bucket-mean
2026.04
26.5
32.8
18.2
Thompson Samp.
2026.04
25.1
31.9
15.6
Static
2026.04
22.3
32.1
8.4
Feedback
Search any
task
Search any
task