Tool-calling on τ-Retail
53.9Average ScoreLedger
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LedgerBackbone=Kimi-K2.52026.06 | 53.9 | 70.6 | 41.2 | |
| LedgerBackbone=GLM-52026.06 | 48.5 | 67.1 | 35.1 | |
| Standard Function Calling (FC)Backbone=GLM-52026.06 | 40.9 | 61 | 26.3 | |
| Standard Function Calling (FC)Backbone=Kimi-K2.52026.06 | 38.3 | 57.5 | 24.6 | |
| LedgerBackbone=MiniMax M2.52026.06 | 36.6 | 58.1 | 21.1 | |
| Standard Function Calling (FC)Backbone=MiniMax M2.52026.06 | 16.7 | 33.6 | 7 |