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

Software Engineering Issue Resolution on SWE-bench Verified

89.2Resolution Rate

MiniMax-M2.5

37.250.764.277.7May 14, 2026May 20, 2026May 27, 2026Jun 3, 2026Jun 9, 2026Jun 16, 2026Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
89.2--
2026.06
87.8--
2026.06
86.2--
2026.06
82.6--
2026.06
80.882.5480.8
2026.06
80.884.1480.6
2026.06
80.4883.380.9
2026.06
80.1683.4-
2026.06
79.5282.2-
2026.06
79.2881.7280
2026.06
7982.0679.6
2026.06
78.3281.7678
2026.06
77.5680.76-
2026.06
76.879.98-
2026.06
76.6--
2026.06
76.479.9477.2
2026.06
76.2480.5277.2
2026.06
76--
2026.06
74.5--
2026.06
74.4--
2026.06
74.3679.572.4
2026.06
73.4--
2026.06
72.9277.7673.4
2026.06
72.8--
2026.06
72.677.373.3
2026.06
72.4478.271.3
2026.06
72.2--
2026.06
7276.8272.7
2026.06
71.8--
2026.06
71--
2026.06
70.4--
2026.06
68.4--
2026.06
68.4--
2026.06
67.5673.6669.6
2026.05
67.5--
2026.06
67.2--
2026.05
66--
2026.05
65--
2026.06
64.6471.962
2026.06
64.6--
2026.05
64.3--
2026.05
64--
2026.06
64--
2026.06
64--
2026.06
63.5--
2026.06
63--
2026.06
63--
2026.06
62.8--
2026.06
62.8--
2026.06
62.6--
2026.05
62.4--
2026.05
62.1--
2026.06
62--
2026.06
61.8--
2026.06
61.6--
2026.05
61.4--
2026.06
61--
2026.05
60.6--
2026.06
59.8468.5460
2026.05
59.8--
2026.05
59.4--
59.2--
2026.06
58.6--
2026.05
58.5--
2026.05
57.8--
2026.06
57.8--
2026.05
57.6--
2026.05
56.1--
2026.06
55.5--
2026.05
54.6--
2026.06
54.6--
2026.06
54--
2026.06
53.2--
2026.06
53.2--
2026.06
53--
2026.05
52.6--
2026.06
52.4--
2026.05
52.2--
2026.06
52.2--
2026.06
52--
2026.05
51.6--
2026.06
51.3659.4651.6
2026.06
50.6--
2026.06
50.4--
2026.06
49.4--
2026.06
49.4--
2026.06
47.8--
2026.06
46--
2026.06
45.4--
2026.06
45.2--
2026.06
44.7--
2026.06
44.6--
2026.06
44.6--
2026.06
43.2--
2026.06
41.6--
2026.06
41.2--
2026.05
40.2--
2026.06
40.2--
2026.06
40.2--
2026.06
39.2--
Showing 100 of 110 rows