Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Feasibility Prediction on SWE-bench

47.6F1@1

Qwen3 235B

31.58435.74239.944.058May 29, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
47.635.132.8
43.540.221.2
41.151.148.8
39.258.252
32.237.723.4