Sales interaction performance on SalesLLM EN 1.0
6.39SalesLLM ScoreGemini-3-pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-proUser Simulator=GPT-4o2026.04 | 6.39 | |
| Doubao-1.5-pro-32kUser Simulator=GPT-4o2026.04 | 6.31 | |
| Qwen2.5-72BUser Simulator=GPT-4o2026.04 | 6.13 | |
| DeepSeek-Chat (V3.1)User Simulator=GPT-4o2026.04 | 6.1 | |
| Gemini-3-proUser Simulator=Custom User2026.04 | 6.03 | |
| Gemini-3-flashUser Simulator=Custom User2026.04 | 6.03 | |
| Qwen-MaxUser Simulator=GPT-4o2026.04 | 5.97 | |
| Gemma-3-27BUser Simulator=GPT-4o2026.04 | 5.97 | |
| Llama-3.3-70BUser Simulator=GPT-4o2026.04 | 5.95 | |
| Gemini-3-flashUser Simulator=GPT-4o2026.04 | 5.94 | |
| GLM-4-9BUser Simulator=GPT-4o2026.04 | 5.92 | |
| GPT-5-NanoUser Simulator=GPT-4o2026.04 | 5.9 | |
| Xiaomi-MiMo-V2User Simulator=Custom User2026.04 | 5.9 | |
| GPT-5-NanoUser Simulator=Custom User2026.04 | 5.84 | |
| DeepSeek-Chat (V3.1)User Simulator=Custom User2026.04 | 5.8 | |
| Qwen3-8BUser Simulator=Custom User2026.04 | 5.79 | |
| Qwen3-32BUser Simulator=GPT-4o2026.04 | 5.76 | |
| Xiaomi-MiMo-V2User Simulator=GPT-4o2026.04 | 5.67 | |
| GLM-4.6User Simulator=GPT-4o2026.04 | 5.64 | |
| Qwen2.5-72BUser Simulator=Custom User2026.04 | 5.63 | |
| Qwen3-32BUser Simulator=Custom User2026.04 | 5.62 | |
| Qwen-MaxUser Simulator=Custom User2026.04 | 5.56 | |
| Qwen3-8BUser Simulator=GPT-4o2026.04 | 5.56 | |
| GLM-4-9BUser Simulator=Custom User2026.04 | 5.55 | |
| GPT-4oUser Simulator=GPT-4o2026.04 | 5.53 | |
| Doubao-1.5-pro-32kUser Simulator=Custom User2026.04 | 5.48 | |
| GLM-4.6User Simulator=Custom User2026.04 | 5.32 | |
| Llama-3.3-70BUser Simulator=Custom User2026.04 | 5.24 | |
| GPT-4oUser Simulator=Custom User2026.04 | 5.19 | |
| Gemma-3-27BUser Simulator=Custom User2026.04 | 5.09 |