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

Tool selection on API-Bench

96.3Accuracy

MTA

32.204848.844965.48582.1251Jan 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
96.3
2026.01
95.11
2026.01
94.77
2026.01
93.8
2026.01
93.3
2026.01
88.34
2026.01
83.12
2026.01
82.45
2026.01
70.33
2026.01
65.34
2026.01
59.1
2026.01
55.12
2026.01
51.79
2026.01
50.23
2026.01
46.34
2026.01
45.02
2026.01
42.48
2026.01
39.12
2026.01
38.91
2026.01
34.67