Continual routing on Average
75.2AccuracyCONCUR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| CONCURSetting=Setting 1: Large models only, Relative training time=1.00x2025.12 | 75.2 | 40.84 | |
| CONCURSetting=Setting 2: Large and small models, Relative training time=1.00x2025.12 | 75.2 | 36.5 | |
| RTRSetting=Setting 2: Large and small models, Relative training time=3.89x, Training Strategy=Fine-tuned (75%)2025.12 | 74.7 | 41.01 | |
| EmbedLLMSetting=Setting 1: Large models only, Relative training time=1.32x, Training Strategy=From scratch (FS)2025.12 | 74.5 | 42.45 | |
| RTRSetting=Setting 1: Large models only, Relative training time=3.93x, Training Strategy=From scratch (FS)2025.12 | 74.4 | 41.64 | |
| Best single strategySetting=Setting 1: Large models only2025.12 | 74.3 | 41.63 | |
| Best single strategySetting=Setting 2: Large and small models2025.12 | 74.3 | 41.63 | |
| RTRSetting=Setting 2: Large and small models, Relative training time=7.66x, Training Strategy=From scratch (FS)2025.12 | 74.3 | 40.52 | |
| EmbedLLMSetting=Setting 2: Large and small models, Relative training time=3.08x, Training Strategy=From scratch (FS)2025.12 | 73.4 | 34.21 | |
| RTRSetting=Setting 2: Large and small models, Relative training time=4.96x, Training Strategy=Fine-tuned (100%)2025.12 | 73.1 | 35.05 | |
| EmbedLLMSetting=Setting 2: Large and small models, Relative training time=3.11x, Training Strategy=Fine-tuned (100%)2025.12 | 73 | 33.99 | |
| RTRSetting=Setting 2: Large and small models, Relative training time=1.69x, Training Strategy=Fine-tuned (25%)2025.12 | 72.7 | 31.85 | |
| RTRSetting=Setting 2: Large and small models, Relative training time=2.84x, Training Strategy=Fine-tuned (50%)2025.12 | 71.9 | 24.95 | |
| EmbedLLMSetting=Setting 2: Large and small models, Relative training time=1.01x, Training Strategy=Fine-tuned (25%)2025.12 | 71.8 | 35.13 | |
| EmbedLLMSetting=Setting 2: Large and small models, Relative training time=1.92x, Training Strategy=Fine-tuned (50%)2025.12 | 71.7 | 31.29 | |
| EmbedLLMSetting=Setting 2: Large and small models, Relative training time=2.82x, Training Strategy=Fine-tuned (75%)2025.12 | 71.6 | 32.09 | |
| RouteLLMSetting=Setting 1: Large models only, Relative training time=0.18x, Training Strategy=From scratch (FS)2025.12 | 70.9 | 31.96 | |
| RouteLLMSetting=Setting 2: Large and small models, Relative training time=0.17x, Training Strategy=Fine-tuned (50%)2025.12 | 53.7 | 11 | |
| RouteLLMSetting=Setting 2: Large and small models, Relative training time=0.20x, Training Strategy=From scratch (FS)2025.12 | 53.5 | 10.2 | |
| RouteLLMSetting=Setting 2: Large and small models, Relative training time=0.23x, Training Strategy=Fine-tuned (100%)2025.12 | 52.8 | 9.74 | |
| RouteLLMSetting=Setting 2: Large and small models, Relative training time=0.14x, Training Strategy=Fine-tuned (25%)2025.12 | 52.2 | 10.23 | |
| RouteLLMSetting=Setting 2: Large and small models, Relative training time=0.20x, Training Strategy=Fine-tuned (75%)2025.12 | 51.2 | 8.7 |