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

Tool-use API Generalization on ToolBench G2

78.2Pass Rate

EVOTOOL

41.851.2560.770.15Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
78.2
2026.03
76.8
2026.03
75.1
2026.03
69.8
2026.03
68.8
2026.03
67.3
2026.03
66.5
2026.03
66.5
2026.03
65.3
2026.03
64.7
2026.03
61.8
2026.03
59.3
2026.03
59.2
2026.03
58.5
2026.03
58.5
2026.03
57.2
2026.03
56.5
2026.03
55
2026.03
50.8
2026.03
50.3
2026.03
49.7
2026.03
43.2