| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Output Length Prediction | LMSYS-Chat-1M (test) | MAE45.71 | 16 | |
| Ranking Prediction | LMSYS-Chat-1M R1 | Kendall's Tau0.5 | 4 | |
| Multi-Objective Routing in LLM Serving | LMSYS-Chat-1M 1.0 (test) | Average EEL0.67 | 3 | |
| Ranking Prediction | LMSYS-Chat-1M GPT-4 | Kendall's Tau0.72 | 3 |