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

Tool Use on BEHEMOTH ToolBench (out-of-distribution)

26.82Success Rate

ACE

23.190424.132725.07526.0173Apr 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
26.82
2026.04
26.67
2026.04
26.67
2026.04
25.3
2026.04
24.09
2026.04
23.33