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

Taxi Domain on Taxi Standard

83.98Accuracy

OpenAI o4-mini

-2.142420.216342.57564.9337Nov 28, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
83.98
2025.11
72.66
2025.11
66.41
2025.11
62.16
2025.11
39.16
2025.11
38.92
2025.11
36.72
2025.11
17.97
2025.11
9.38
2025.11
6.64
2025.11
6.25
2025.11
5.6
2025.11
2.34
2025.11
1.17