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

End-to-end Tool-use on ToolBench I3 v1

52.19SoPR

ToolWeaver

9.279620.419831.5642.7002Jan 29, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.01
52.1959.02
2026.01
52.1959.02
2026.01
51.3731.15
2026.01
47.5434.42
2026.01
36.3449.18
2026.01
36.3449.18
2026.01
34.721.31
2026.01
34.4337.7
2026.01
24.86-
2026.01
24.8644.26
2026.01
10.9324.59
2026.01
10.9324.59