Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Tool-use on BFCL Multi-turn

54.75Accuracy

Claude-Sonnet-4

21.958830.471938.98547.4981Dec 22, 2025Dec 29, 2025Jan 5, 2026Jan 12, 2026Jan 19, 2026Jan 26, 2026Feb 3, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
54.7555.91----
2025.12
52.12-59593951.5
2026.02
44.8869.75----
2025.12
44.5-54.54136.546
2026.02
43.7568.69----
2025.12
41.25-51433140
2026.02
40.4452.47----
2025.12
40.12-494129.541
2026.02
38.8850.72----
2025.12
37.88-45.5392443
2025.12
37.75-46.537.52443
2026.02
37.0345.92----
2025.12
37-47312842
2026.02
36.6648.99----
2026.02
36.6341.5----
2025.12
36.12-44312643.5
2026.02
35.9151.85----
2026.02
33.2234.74----
2026.02
29.4141.48----
2026.02
29.2544.99----
2025.12
28.5-33.529.52328
2026.02
27.2542.81----
2025.12
25-25.52624.524
2026.02
23.2245.29----