Bargaining on AmazonHistoryPrice MI 1.0 (test)
835CountChatGPT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ChatGPTRole=Buyer2024.02 | 835 | 34.01 | -157.73 | |
| GPT-4Role=Buyer2024.02 | 807 | 37.55 | -23.46 | |
| Mistral-7B-InstructRole=Buyer2024.02 | 748 | 44.92 | -77.32 | |
| Yi-34B-ChatRole=Buyer2024.02 | 722 | 33.66 | -111.2 | |
| Llama-2-13b-chatRole=Buyer2024.02 | 682 | 56.3 | -270.11 | |
| Llama-2-70b-chatRole=Buyer2024.02 | 625 | 47.36 | -335.93 | |
| Baichuan2-7B-ChatRole=Buyer2024.02 | 623 | 50.4 | -567.11 | |
| Qwen-7B-ChatRole=Buyer2024.02 | 615 | 62.44 | -692.12 | |
| Llama-2-7b-chatRole=Buyer2024.02 | 576 | 45.83 | -279.6 | |
| Yi-6B-ChatRole=Buyer2024.02 | 532 | 27.44 | -116.16 | |
| Qwen-14B-ChatRole=Buyer2024.02 | 529 | 44.61 | -121.24 | |
| ChatGLM3-6BRole=Buyer2024.02 | 516 | 38.57 | -219.25 | |
| Baichuan2-13B-ChatRole=Buyer2024.02 | 484 | 30.58 | -237.84 | |
| Mixtral-8x7B-InstructRole=Buyer2024.02 | 475 | 31.79 | -59.66 |