Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering Problem Solving on SWE-Bench Verified
Loading...
25.8
Rounds Taken
Mini SWE Agent + LaMR
24.792
31.596
38.4
45.204
May 14, 2026
Rounds Taken
Solved Count
Success Rate
Success Rate Delta (%)
Tokens Used (M)
Tokens Used Delta (%)
Updated 2mo ago
Evaluation Results
Method
Method
Links
Rounds Taken
Solved Count
Success Rate
Success Rate Delta (%)
Tokens Used (M)
Tokens Used Delta (%)
Mini SWE Agent + LaMR
Backbone Model=Claude...
2026.05
25.8
380
76
0.4
0.453
3
Mini SWE Agent + SWE-Pruner
Backbone Model=Claude...
2026.05
26.8
383
76.6
1
0.498
6.6
Mini SWE Agent
Backbone Model=Claude...
2026.05
30.9
378
75.6
-
0.467
-
Mini SWE Agent + LaMR
Backbone Model=Claude...
2026.05
39.6
359
71.8
1.2
0.633
30.5
Mini SWE Agent + SWE-Pruner
Backbone Model=Claude...
2026.05
41.7
360
72
1.4
0.701
23.1
Mini SWE Agent
Backbone Model=Claude...
2026.05
51
353
70.6
-
0.911
-
Feedback
Search any
task
Search any
task