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

Tool Use on API-Bank (test)

75.54Overall Accuracy

CAHL

49.90456.559563.21569.8705Jun 8, 2026Jun 9, 2026Jun 10, 2026Jun 11, 2026Jun 12, 2026Jun 13, 2026Jun 15, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
75.54-81.764.262.6--
2026.06
73.7-76.1953.7376.34--
2026.06
64.99-73.265.739.7--
2026.06
62.88-69.2757.6146.1111.629
2026.06
62.35-68.5758.2145.4911.624
2026.06
61.81-72.256.732.8--
2026.06
61.57-67.4256.1246.5711.616
2026.06
61.24-67.2256.4245.50.991.602
2026.06
60.47-70.746.336.6--
2026.06
58.79-64.8143.8848.0911.588
2026.06
58.79-64.1142.395111.588
2026.06
58.29-65.443.344.3--
2026.06
57.05-63.9144.7842.4411.571
2026.06
55.44-60.9542.6945.1911.554
2026.06
54.61-61.1535.8244.27--
2026.06
52.96-59.9544.4836.030.991.52
2026.06
52.36-58.5945.9736.6411.524
2026.06
51.46-56.5943.28400.991.505
2026.06
50.89-56.6944.7836.3311.509
2024.07
-82.6-----
2024.07
-56.5-----
2024.07
-55.8-----
2024.07
-90-----
2024.07
-73.1-----
2024.07
-60.9-----
2024.07
-92.3-----
2024.07
-89-----
2024.07
-91.3-----
2024.07
-92.6-----
2026.03
-38.7-----
2026.03
-52.4-----
2026.03
-63.5-----
-67.1-----
-66.7-----
2026.03
-71.8-----