Tool-calling on τ-Telehealth
20.7Average ScoreLedger
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LedgerBackbone=MiniMax M2.52026.06 | 20.7 | 28.8 | 15 | |
| LedgerBackbone=Kimi-K2.52026.06 | 18.8 | 25 | 15.8 | |
| LedgerBackbone=GLM-52026.06 | 17.6 | 27.5 | 10 | |
| Standard Function Calling (FC)Backbone=GLM-52026.06 | 16.9 | 20 | 15.8 | |
| Standard Function Calling (FC)Backbone=Kimi-K2.52026.06 | 11.3 | 15 | 10 | |
| Standard Function Calling (FC)Backbone=MiniMax M2.52026.06 | 10.7 | 18.8 | 5 |