Sales interaction performance on SalesLLM Chinese (ZH) 1.0
7.14SalesLLM ScoreGLM-4-9B
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-4-9BUser Simulator=Custom User2026.04 | 7.14 | |
| DeepSeek-Chat (V3.1)User Simulator=Custom User2026.04 | 7.03 | |
| Doubao-1.5-pro-32kUser Simulator=Custom User2026.04 | 6.89 | |
| GLM-4.6User Simulator=Custom User2026.04 | 6.86 | |
| DeepSeek-Chat (V3.1)User Simulator=GPT-4o2026.04 | 6.74 | |
| GLM-4.6User Simulator=GPT-4o2026.04 | 6.74 | |
| Gemini-3-proUser Simulator=GPT-4o2026.04 | 6.52 | |
| Doubao-1.5-pro-32kUser Simulator=GPT-4o2026.04 | 6.5 | |
| Qwen-MaxUser Simulator=GPT-4o2026.04 | 6.48 | |
| Human GroupUser Simulator=GPT-4o2026.04 | 6.33 | |
| GPT-4oUser Simulator=GPT-4o2026.04 | 6.16 | |
| GPT-4oUser Simulator=Custom User2026.04 | 6.15 | |
| Qwen2.5-72BUser Simulator=GPT-4o2026.04 | 6.06 | |
| GLM-4-9BUser Simulator=GPT-4o2026.04 | 6.01 | |
| Gemini-3-proUser Simulator=Custom User2026.04 | 5.93 | |
| Gemini-3-flashUser Simulator=Custom User2026.04 | 5.93 | |
| GPT-5-NanoUser Simulator=Custom User2026.04 | 5.92 | |
| Gemma-3-27BUser Simulator=GPT-4o2026.04 | 5.9 | |
| Qwen3-32BUser Simulator=GPT-4o2026.04 | 5.81 | |
| Qwen3-32BUser Simulator=Custom User2026.04 | 5.79 | |
| Llama-3.3-70BUser Simulator=GPT-4o2026.04 | 5.74 | |
| Gemini-3-flashUser Simulator=GPT-4o2026.04 | 5.71 | |
| Qwen2.5-72BUser Simulator=Custom User2026.04 | 5.7 | |
| Gemma-3-27BUser Simulator=Custom User2026.04 | 5.66 | |
| Xiaomi-MiMo-V2User Simulator=GPT-4o2026.04 | 5.65 | |
| Qwen3-8BUser Simulator=Custom User2026.04 | 5.64 | |
| Xiaomi-MiMo-V2User Simulator=Custom User2026.04 | 5.59 | |
| Qwen-MaxUser Simulator=Custom User2026.04 | 5.55 | |
| Qwen3-8BUser Simulator=GPT-4o2026.04 | 5.4 | |
| Llama-3.3-70BUser Simulator=Custom User2026.04 | 5.32 | |
| GPT-5-NanoUser Simulator=GPT-4o2026.04 | 5.22 |