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

Tool-use on ToolBench (Avg token length, TSR, ASR)

99.61Average Success Rate (ASR)

Llama 3.3-70B

-0.760425.297351.35577.4127Jan 16, 2026Feb 6, 2026Feb 27, 2026Mar 21, 2026Apr 11, 2026May 2, 2026May 24, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.01
99.61389-
2026.01
96.1781,830-
2026.01
91.41725-
2026.05
84.7--
2026.01
84.2985,037-
2026.01
83.564,223-
2026.01
83.1463,694-
2026.05
81.6--
2026.01
81.2361,354-
2026.05
80.8--
2026.01
80.4665,273-
2026.01
80.088,743-
2026.05
79.6--
2026.01
79.31,453-
2026.01
78.9365,546-
2026.05
78--
2026.05
77.6--
2026.05
74.7--
2026.05
72.4--
2026.05
71.2--
2026.05
70.4--
2026.05
68.2--
2026.05
66.3--
2026.05
66.1--
2026.05
65.4--
2026.05
64.8--
2026.05
64.3--
2026.05
63.3--
2026.05
62.9--
2026.05
58.4--
2026.01
57.5412,580-
2026.05
55.2--
2026.05
55.1--
2026.05
53.1--
2026.05
47.1--
2026.05
46.9--
2026.05
44.5--
2026.05
35.7--
2026.05
35.7--
2026.05
33.3--
2026.05
31.6--
2026.05
29.6--
2026.05
27.6--
2026.05
27.3--
2026.05
26.6--
2026.05
26.1--
2026.05
23.7--
2026.05
21.4--
2026.05
21.1--
2026.05
20.4--
2026.05
20.4--
2026.05
19.4--
2026.05
18.3--
2026.05
17.1--
2026.05
16.3--
2026.05
16.2--
2026.05
15.7--
2026.05
12.9--
2026.05
9.2--
2026.05
8.1--
2026.05
4.1--
2026.05
3.1--
2026.01
-26098.08
2026.01
-63894.64
2026.01
-63495.02
2026.01
-12790.8
2026.01
-19786.59
2026.01
-1,29890.42