Bargaining on AmazonHistoryPrice ALL 1.0 (test)
930CountGPT-4
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4Role=Seller2024.02 | 930 | 1,178.15 | 137.31 | |
| Yi-34B-ChatRole=Seller2024.02 | 899 | 579.33 | 86.6 | |
| ChatGPTRole=Buyer2024.02 | 877 | -164.52 | -59.61 | |
| ChatGPTRole=Seller2024.02 | 877 | 440.52 | 159.61 | |
| GPT-4Role=Buyer2024.02 | 851 | -33.81 | -11.27 | |
| Llama-2-70b-chatRole=Seller2024.02 | 837 | 415.28 | 64.38 | |
| Mistral-7B-InstructRole=Seller2024.02 | 830 | 526.5 | 78.58 | |
| Qwen-14B-ChatRole=Seller2024.02 | 795 | 393.16 | 71.1 | |
| Qwen-7B-ChatRole=Seller2024.02 | 793 | 92.86 | 37.14 | |
| Mistral-7B-InstructRole=Buyer2024.02 | 786 | -89.17 | -27.87 | |
| Baichuan2-7B-ChatRole=Seller2024.02 | 762 | 38.29 | 6.36 | |
| Yi-34B-ChatRole=Buyer2024.02 | 761 | -129.76 | -54.52 | |
| Baichuan2-13B-ChatRole=Seller2024.02 | 741 | -211.92 | -48.16 | |
| Llama-2-13b-chatRole=Seller2024.02 | 727 | 308.21 | 62.9 | |
| Llama-2-13b-chatRole=Buyer2024.02 | 720 | -305.53 | -82.35 | |
| ChatGLM3-6BRole=Seller2024.02 | 701 | 91.1 | 17.83 | |
| Llama-2-70b-chatRole=Buyer2024.02 | 660 | -361.26 | -127.2 | |
| Baichuan2-7B-ChatRole=Buyer2024.02 | 653 | -603.67 | -199.23 | |
| Qwen-7B-ChatRole=Buyer2024.02 | 647 | -753.16 | -201.92 | |
| Llama-2-7b-chatRole=Buyer2024.02 | 612 | -288.59 | -113.17 | |
| Mixtral-8x7B-InstructRole=Seller2024.02 | 600 | 483.99 | 110.75 | |
| Qwen-14B-ChatRole=Buyer2024.02 | 562 | -159.21 | -70.13 | |
| Yi-6B-ChatRole=Buyer2024.02 | 561 | -122.94 | -87.19 | |
| ChatGLM3-6BRole=Buyer2024.02 | 546 | -261.91 | -137.13 | |
| Baichuan2-13B-ChatRole=Buyer2024.02 | 510 | -216.67 | -152.59 | |
| Mixtral-8x7B-InstructRole=Buyer2024.02 | 505 | -63.19 | -43.28 | |
| Llama-2-7b-chatRole=Seller2024.02 | 496 | 49.54 | 16.24 | |
| Yi-6B-ChatRole=Seller2024.02 | 64 | 14.14 | 27.72 |