Multi-Hop QA on Zh.QA
48.2F1 ScoreEXTAGENTS
Evaluation Results
| Method | Links | |
|---|---|---|
| EXTAGENTSBackbone=gpt-4o-mini-2024-07-18, Input length=1024k2025.05 | 48.2 | |
| LLM×MapReduceBackbone=gpt-4o-mini-2024-07-18, Input length=128k2025.05 | 43.6 | |
| EXTAGENTSBackbone=Llama-3.1-8B-Instruct, Input length=256k2025.05 | 34.7 | |
| LLM×MapReduceBackbone=Llama-3.1-8B-Instruct, Input length=128k2025.05 | 34.5 | |
| Direct InputBackbone=Llama-3.1-8B-Instruct, Input length=128k2025.05 | 31.5 | |
| Chain of AgentsBackbone=Llama-3.1-8B-Instruct, Input length=32k2025.05 | 24.6 | |
| Direct InputBackbone=gpt-4o-mini-2024-07-18, Input length=128k2025.05 | 20.4 | |
| Direct InputBackbone=DeepSeek-R1-Distill-Llama-8B, Input length=32k2025.05 | 14.3 |