# Sales interaction performance on SalesLLM Chinese (ZH) 1.0 Source: [Sales interaction performance on SalesLLM Chinese (ZH) 1.0]() Collection index: [llms.txt]() Data updated: 2026-04-10T00:48:23.260Z Evaluation of sales interaction performance using the SalesLLM Score metric on the SalesLLM Chinese (ZH) 1.0 dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Sales interaction performance | | Dataset (including any stated split) | SalesLLM Chinese (ZH) 1.0 | | Metric | SalesLLM Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 31 of 31 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [SalesLLM Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | SalesLLM Score | Result date | Report paper | | --- | --- | --- | --- | | GLM-4-9B | 7.14 | Not recorded | 69d732917d0172140ec76b1e | | DeepSeek-Chat (V3.1) | 7.03 | Not recorded | 69d732917d0172140ec76b1e | | Doubao-1.5-pro-32k | 6.89 | Not recorded | 69d732917d0172140ec76b1e | | GLM-4.6 | 6.86 | Not recorded | 69d732917d0172140ec76b1e | | DeepSeek-Chat (V3.1) | 6.74 | Not recorded | 69d732917d0172140ec76b1e | | GLM-4.6 | 6.74 | Not recorded | 69d732917d0172140ec76b1e | | Gemini-3-pro | 6.52 | Not recorded | 69d732917d0172140ec76b1e | | Doubao-1.5-pro-32k | 6.5 | Not recorded | 69d732917d0172140ec76b1e | | Qwen-Max | 6.48 | Not recorded | 69d732917d0172140ec76b1e | | Human Group | 6.33 | Not recorded | 69d732917d0172140ec76b1e | | GPT-4o | 6.16 | Not recorded | 69d732917d0172140ec76b1e | | GPT-4o | 6.15 | Not recorded | 69d732917d0172140ec76b1e | | Qwen2.5-72B | 6.06 | Not recorded | 69d732917d0172140ec76b1e | | GLM-4-9B | 6.01 | Not recorded | 69d732917d0172140ec76b1e | | Gemini-3-pro | 5.93 | Not recorded | 69d732917d0172140ec76b1e | | Gemini-3-flash | 5.93 | Not recorded | 69d732917d0172140ec76b1e | | GPT-5-Nano | 5.92 | Not recorded | 69d732917d0172140ec76b1e | | Gemma-3-27B | 5.9 | Not recorded | 69d732917d0172140ec76b1e | | Qwen3-32B | 5.81 | Not recorded | 69d732917d0172140ec76b1e | | Qwen3-32B | 5.79 | Not recorded | 69d732917d0172140ec76b1e | | Llama-3.3-70B | 5.74 | Not recorded | 69d732917d0172140ec76b1e | | Gemini-3-flash | 5.71 | Not recorded | 69d732917d0172140ec76b1e | | Qwen2.5-72B | 5.7 | Not recorded | 69d732917d0172140ec76b1e | | Gemma-3-27B | 5.66 | Not recorded | 69d732917d0172140ec76b1e | | Xiaomi-MiMo-V2 | 5.65 | Not recorded | 69d732917d0172140ec76b1e | | Qwen3-8B | 5.64 | Not recorded | 69d732917d0172140ec76b1e | | Xiaomi-MiMo-V2 | 5.59 | Not recorded | 69d732917d0172140ec76b1e | | Qwen-Max | 5.55 | Not recorded | 69d732917d0172140ec76b1e | | Qwen3-8B | 5.4 | Not recorded | 69d732917d0172140ec76b1e | | Llama-3.3-70B | 5.32 | Not recorded | 69d732917d0172140ec76b1e | | GPT-5-Nano | 5.22 | Not recorded | 69d732917d0172140ec76b1e | ### GLM-4-9B SalesLLM Score: 7.14. Result ID: 69d8485b47f34ce924c07eb8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### DeepSeek-Chat (V3.1) SalesLLM Score: 7.03. Result ID: 69d8485b47f34ce924c07eb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Doubao-1.5-pro-32k SalesLLM Score: 6.89. Result ID: 69d8485b47f34ce924c07eb0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### GLM-4.6 SalesLLM Score: 6.86. Result ID: 69d8485b47f34ce924c07eba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### DeepSeek-Chat (V3.1) SalesLLM Score: 6.74. Result ID: 69d8485b47f34ce924c07eb3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### GLM-4.6 SalesLLM Score: 6.74. Result ID: 69d8485b47f34ce924c07eb9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Gemini-3-pro SalesLLM Score: 6.52. Result ID: 69d8485b47f34ce924c07ebb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Doubao-1.5-pro-32k SalesLLM Score: 6.5. Result ID: 69d8485b47f34ce924c07eaf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Qwen-Max SalesLLM Score: 6.48. Result ID: 69d8485b47f34ce924c07eb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Human Group SalesLLM Score: 6.33. Result ID: 69d8485b47f34ce924c07ecd. [Reporting paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### GPT-4o SalesLLM Score: 6.16. Result ID: 69d8485b47f34ce924c07eb5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### GPT-4o SalesLLM Score: 6.15. Result ID: 69d8485b47f34ce924c07eb6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Qwen2.5-72B SalesLLM Score: 6.06. Result ID: 69d8485b47f34ce924c07ec1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### GLM-4-9B SalesLLM Score: 6.01. Result ID: 69d8485b47f34ce924c07eb7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Gemini-3-pro SalesLLM Score: 5.93. Result ID: 69d8485b47f34ce924c07ebc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Gemini-3-flash SalesLLM Score: 5.93. Result ID: 69d8485b47f34ce924c07ecc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### GPT-5-Nano SalesLLM Score: 5.92. Result ID: 69d8485b47f34ce924c07ec8. [Reporting paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Gemma-3-27B SalesLLM Score: 5.9. Result ID: 69d8485b47f34ce924c07ec3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Qwen3-32B SalesLLM Score: 5.81. Result ID: 69d8485b47f34ce924c07ebf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Qwen3-32B SalesLLM Score: 5.79. Result ID: 69d8485b47f34ce924c07ec0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Llama-3.3-70B SalesLLM Score: 5.74. Result ID: 69d8485b47f34ce924c07ec5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Gemini-3-flash SalesLLM Score: 5.71. Result ID: 69d8485b47f34ce924c07ecb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Qwen2.5-72B SalesLLM Score: 5.7. Result ID: 69d8485b47f34ce924c07ec2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Gemma-3-27B SalesLLM Score: 5.66. Result ID: 69d8485b47f34ce924c07ec4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Xiaomi-MiMo-V2 SalesLLM Score: 5.65. Result ID: 69d8485b47f34ce924c07ec9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Qwen3-8B SalesLLM Score: 5.64. Result ID: 69d8485b47f34ce924c07ebe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Xiaomi-MiMo-V2 SalesLLM Score: 5.59. Result ID: 69d8485b47f34ce924c07eca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Qwen-Max SalesLLM Score: 5.55. Result ID: 69d8485b47f34ce924c07eb2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### Qwen3-8B SalesLLM Score: 5.4. Result ID: 69d8485b47f34ce924c07ebd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. ### Llama-3.3-70B SalesLLM Score: 5.32. Result ID: 69d8485b47f34ce924c07ec6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"User Simulator":"Custom User"}. This record does not assert independent reproduction. ### GPT-5-Nano SalesLLM Score: 5.22. Result ID: 69d8485b47f34ce924c07ec7. [Reporting paper]() Recorded evaluation configuration: {"User Simulator":"GPT-4o"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.