Tool Selection on ToolE (test)
67.35Recall@1L_PORTS
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| L_PORTSEncoder=BGE, Best LLM=CODESTRAL-22B-v0.12026.07 | 67.35 | 79.48 | 83.75 | 67.35 | 77 | 78 | 14.71 | 14.12 | |
| L_replugEncoder=BGE, Best LLM=LLAMA3-GROQ-8B-Tool-Use2026.07 | 67.23 | 77.54 | 81.06 | 67.23 | 75.5 | 76.82 | 13.12 | 13.18 | |
| L_PORTSEncoder=RoBERTa, Best LLM=LLAMA3-8B2026.07 | 60.33 | 72.45 | 77.15 | 60.33 | 70.29 | 72.34 | 57.51 | 55.65 | |
| L_replugEncoder=RoBERTa, Best LLM=LLAMA3-GROQ-8B-Tool-Use2026.07 | 49.38 | 59.84 | 64.23 | 49.38 | 58.17 | 60.79 | 45.35 | 44.11 |