Question Answering on ∞Bench En.QA
42.1F1 ScoreEXTAGENTS
Evaluation results
| Method | Links | |
|---|---|---|
| EXTAGENTSBase Model=gpt-4o-mini-2024-07-18, Input (#tokens)=1024k2025.05 | 42.1 | |
| LLM×MapReduceBase Model=gpt-4o-mini-2024-07-18, Input (#tokens)=128k2025.05 | 38.5 | |
| EXTAGENTSBase Model=Llama-3.1-8B-Instruct, Input (#tokens)=512k2025.05 | 32.2 | |
| LLM×MapReduceBase Model=Llama-3.1-8B-Instruct, Input (#tokens)=256k2025.05 | 28.7 | |
| Direct InputBase Model=Llama-3.1-8B-Instruct, Input (#tokens)=128k2025.05 | 26.7 | |
| Direct InputBase Model=gpt-4o-mini-2024-07-18, Input (#tokens)=128k2025.05 | 18.9 | |
| Direct InputBase Model=DeepSeek-R1-Distill-Llama-8B, Input (#tokens)=32k2025.05 | 10.4 |