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

Tool-use Reasoning on ToolQA

47.97Accuracy

Full Text

-1.918811.033123.98536.9369Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
47.971,010
2026.06
46.92754
2026.06
45.45769
2026.06
43.92512
2026.06
43.08573
2026.06
37.06294
2026.06
35.66256
2026.06
28.040
2026.06
26.78512
2026.06
23.08256
2026.06
17.27705
2026.06
15.24755
2026.06
14.830
2026.06
14.48561
2026.06
9.79996
2026.06
7.13256
2026.06
4.48287
2026.06
0256
2026.06
0256
2026.06
0256