Customer Service on TauBench-Telephony (TBTel)
90.5AccuracyLLM-guided spec search
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLM-guided spec searchStudent Model=Qwen3.5-9B, Optimization Status=Optimized, Teacher Selection=Best teacher per benchmark2026.05 | 90.5 | 15.2 | |
| Qwen3.5-9BStudent Model=Qwen3.5-9B, Optimization Status=Base2026.05 | 75.3 | — | |
| LLM-guided spec searchStudent Model=Gemma4-E4B, Optimization Status=Optimized, Teacher Selection=Best teacher per benchmark2026.05 | 75 | 13.7 | |
| Gemma4-E4BStudent Model=Gemma4-E4B, Optimization Status=Base2026.05 | 61.3 | — | |
| LLM-guided spec searchStudent Model=Nemotron-Nano-4B, Optimization Status=Optimized, Teacher Selection=Best teacher per benchmark2026.05 | 11.4 | 11.4 | |
| LLM-guided spec searchStudent Model=Qwen3.5-4B, Optimization Status=Optimized, Teacher Selection=Best teacher per benchmark2026.05 | 9.4 | 9.4 | |
| Nemotron-Nano-4BStudent Model=Nemotron-Nano-4B, Optimization Status=Base2026.05 | 0 | — | |
| Qwen3.5-4BStudent Model=Qwen3.5-4B, Optimization Status=Base2026.05 | 0 | — |