# Sell More, Play Less: Benchmarking LLM Realistic Selling Skill

Source: [Sell More, Play Less: Benchmarking LLM Realistic Selling Skill](<https://www.sota2.com/research/paper/69d732917d0172140ec76b1e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-11T05:00:04.810Z

Authors: Xuanbo Su, Wenhao Hu, Haibo Su, Yunzhang Chen, Le Zhan, Yanqi Yang, Leo Huang

Published: 2026-04-08T13:06:37.000Z

## Abstract

Sales dialogues require multi-turn, goal-directed persuasion under asymmetric incentives, which makes them a challenging setting for large language models (LLMs). Yet existing dialogue benchmarks rarely measure deal progression and outcomes. We introduce SalesLLM benchmark, a bilingual (ZH/EN) benchmark derived from realistic applications covering Financial Services and Consumer Goods, built from 30,074 scripted configurations and 1,805 curated multi-turn scenarios with controllable difficulty and personas. We propose a fully automatic evaluation pipeline that combines (i) an LLM-based rater for sales-process progress,and (ii) fine-tuned BERT classifiers for end-of-dialogue buying intent. To improve simulation fidelity, we train a user model, CustomerLM, with SFT and DPO on 8,000+ crowdworker-involved sales conversations, reducing role inversion from 17.44% (GPT-4o) to 8.8%. SalesLLM benchmark scores correlate strongly with expert human ratings (Pearson r=0.98). Experiments across 15 mainstream LLMs reveal substantial variability: top-performance LLMs are competitive with human-level performance while the less capable ones are worse than human. SalesLLM benchmark serves as a scalable benchmark for developing and evaluating outcome-oriented sales agents.

## Recorded benchmark results

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.

- [Sales interaction performance on SalesLLM Chinese (ZH) 1.0](<https://www.sota2.com/research/sota/sales-interaction-performance-on-salesllm-chinese-zh-1-0.md>): Sales interaction performance; SalesLLM Chinese (ZH) 1.0; SalesLLM Score: not recorded.

- [Sales interaction performance on SalesLLM EN 1.0](<https://www.sota2.com/research/sota/sales-interaction-performance-on-salesllm-en-1-0.md>): Sales interaction performance; SalesLLM EN 1.0; SalesLLM Score: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.07054>)

[PDF](<https://arxiv.org/pdf/2604.07054.pdf>)