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

Machine Learning Engineering on MLE-Bench Lite

86.36Any Medal (%)

Arbor

15.473633.876852.2870.6832Aug 13, 2025Oct 2, 2025Nov 21, 2025Jan 10, 2026Mar 1, 2026Apr 20, 2026Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
86.36-77.2710095.4509.09
2026.06
81.82-31.8210086.3618.1831.82
2026.06
81.82-40.910086.3613.6427.27
2026.06
77.27-37.8810081.8213.6425.76
2026.06
77.27-39.3977.2777.2712.1225.76
2026.04
75.8316-----
2026.06
75.76-30.310084.8513.6431.82
2026.06
75.76-40.9110086.3615.1519.7
2026.06
74.24-53.0310089.396.0615.15
2026.05
68.18-45.45----
2026.06
68.18-33.3377.2774.2412.1222.73
2026.06
68.18-30.368.1868.1818.1819.7
2026.06
68.18-46.9710081.821.5219.7
2026.06
62.12-34.8510078.7910.6116.67
2026.05
59.09-27.27----
2026.06
55-34.3210070.457.9512.73
2025.08
51.5------
2025.08
48.5------
2026.06
48.48-30.310074.244.5513.64
2025.08
48.18------
2026.06
45.45-31.8277.2754.554.559.09
2025.08
43.9------
2026.05
40.91-27.27----
2026.05
36.36-22.12----
2026.05
35.91-22.73----
2025.08
34.3------
2026.05
22.73-18.18----
2026.04
18.2------