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

Single-hop Tool Calling on WHEN2TOOL single-hop 1.0 (test)

94.3Accuracy

PROBE&PREFILL

23.5841.9460.378.66May 10, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
94.32,128
2026.05
94.12,404
2026.05
94.11,509
2026.05
941,996
2026.05
93.72,421
2026.05
93.72,211
2026.05
93.72,150
2026.05
93.52,175
2026.05
93.52,394
2026.05
93.42,172
2026.05
93.31,912
2026.05
93.21,845
2026.05
93.21,493
2026.05
92.91,823
2026.05
92.82,559
2026.05
92.41,634
2026.05
92.41,227
2026.05
922,435
2026.05
921,589
2026.05
91.12,216
2026.05
90.91,651
2026.05
90.41,707
2026.05
90.11,155
2026.05
89.22,118
2026.05
89.22,804
2026.05
892,507
2026.05
88.82,512
2026.05
88.62,902
2026.05
88.62,828
2026.05
88.51,309
2026.05
88.42,976
2026.05
88.32,128
2026.05
88.32,871
2026.05
88.22,709
2026.05
87.91,231
2026.05
87.22,787
2026.05
86.83,120
2026.05
86.72,475
2026.05
85.8907
2026.05
85.71,852
2026.05
85.51,034
2026.05
84.81,026
2026.05
84.71,923
2026.05
84.43,988
2026.05
84.23,431
2026.05
841,871
2026.05
83.5928
2026.05
83.41,024
2026.05
83.41,027
2026.05
83.14,377
2026.05
82.53,615
2026.05
82.3896
2026.05
81.61,415
2026.05
81.42,868
2026.05
79.53,708
2026.05
78.74,081
2026.05
78.35,302
2026.05
77.73,548
2026.05
77.63,391
2026.05
77.31,020
2026.05
74.7657
2026.05
74.3596
2026.05
73.21,161
2026.05
72.5535
2026.05
71.5604
2026.05
71.11,117
2026.05
70.7484
2026.05
70.21,611
2026.05
69.72,381
2026.05
69.23,027
2026.05
68.92,770
2026.05
66.8451
2026.05
66.52,146
2026.05
66347
2026.05
64.5315
2026.05
61.71,753
2026.05
54.80
2026.05
54.10
2026.05
51.285
2026.05
50.8121
2026.05
47.90
2026.05
47.9293
2026.05
47.60
2026.05
42.40
2026.05
36.30
2026.05
34.56
2026.05
3211
2026.05
31.22
2026.05
29.39
2026.05
26.3293