LLM Routing on Heterogeneous four-agent system Gemma, Phi, Qwen (test)
94Accuracy
Oracle
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.10 | 94 | 0.41 | 86 | |
2025.10 | 94 | 0.41 | 74 | |
2025.10 | 94 | 0.41 | 61 | |
2025.10 | 85 | 0.9 | 67 | |
2025.10 | 85 | 0.9 | 40 | |
2025.10 | 85 | 0.9 | 13 | |
2025.10 | 82 | 0.72 | 68 | |
2025.10 | 82 | 0.64 | 69 | |
2025.10 | 82 | 0.56 | 71 | |
2025.10 | 81 | 0.68 | 67 | |
2025.10 | 81 | 0.7 | 46 | |
2025.10 | 80 | 0.59 | 51 | |
2025.10 | 80 | 0.53 | 54 | |
2025.10 | 80 | 0.58 | 34 | |
2025.10 | 80 | 0.52 | 38 | |
2025.10 | 78 | 0.64 | 65 | |
2025.10 | 78 | 0.64 | 46 | |
2025.10 | 78 | 0.64 | 27 | |
2025.10 | 71 | 0.56 | 60 | |
2025.10 | 71 | 0.56 | 43 | |
2025.10 | 70 | 0.56 | 25 | |
2025.10 | 66 | 0.35 | 49 | |
2025.10 | 51 | 0.26 | 30 | |
2025.10 | 49 | 0.19 | 34 | |
2025.10 | 41 | 0.15 | 38 | |
2025.10 | 41 | 0.15 | 34 | |
2025.10 | 41 | 0.15 | 29 |