Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering Problem Solving on SWE-Bench hard problem subset
Loading...
10.67
Add. Solved
LeanEvolve
4.43
6.05
7.67
9.29
Jun 2, 2026
Add. Solved
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Add. Solved
Overall Score
LeanEvolve
Model=Qwen-3.5-27B
2026.06
10.67
60
LeanEvolve
Model=Kimi-K2.5
2026.06
8.67
70
LeanEvolve
Model=GPT-5.2
2026.06
8
70.67
LeanEvolve
Model=Gemma-4-31B
2026.06
5.33
65.33
LeanEvolve
Model=GLM-5
2026.06
4.67
62.67
Feedback
Search any
task
Search any
task