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

Tool-calling on SupChain-Bench

75.51Accuracy

SupChain-ReAct

2.283621.294340.30559.3157Feb 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
75.51
2026.02
75.51
2026.02
72.44
2026.02
40.81
2026.02
40.81
2026.02
39.79
2026.02
37.56
2026.02
35.7
2026.02
34.69
2026.02
33.67
2026.02
31.63
2026.02
29.59
2026.02
28.57
2026.02
28.57
2026.02
26.53
2026.02
21.42
2026.02
20.4
2026.02
19.38
2026.02
16.32
2026.02
16.32
2026.02
12.24
2026.02
11.22
2026.02
11.22
2026.02
11.22
2026.02
8.16
2026.02
7.14
2026.02
5.1