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

Machine Learning Engineering on MLE-Bench full official

68.2Medal Rate (Low)

Gome (GPT-5)

1.6418.9236.253.48Mar 2, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.03
68.221.122.235.19645.316.4
2026.03
59.120.222.232.594.243.117.3
2026.03
552221.731.697.545.517.3
2026.03
51.510.517.82498.234.712.4
2026.03
509.72023.488.935.112.4
2026.03
479.72022.791.632.912.4
2026.03
42.412.32022.794.231.513.3
2026.03
34.38.81016.982.829.49.4
2026.03
193.25.68.654.914.45
2026.03
11.52.21.95.1527.12.7
2026.03
4.2001.344.31.90.8