ant-intl/BizAgentBench
Dataset · https://huggingface.co/datasets/ant-intl/BizAgentBench
BizAgentBench Paper | Evaluation code | Dataset BizAgentBench evaluates long-horizon agents on 50 payment-service tasks through multi-turn customer conversations and tool use. The tasks combine information gathering, business operations, and constraints on both final outcomes and intermediate actions. This repository contains the task contracts, customer scenarios, knowledge documents, initial database states, and business-tool definitions. The executable environment, user… See the full description on the dataset page: https://huggingface.co/datasets/ant-intl/BizAgentBench.
First seen by Oriel on .
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric · First and latest retained
Likes
Total likes reported by the source.
- Hugging Face Datasets: 21, latest observation ; +2 over observed period since
Downloads (30d)
Rolling 30-day downloads. A change in this value is not new downloads during the observed period.
- Hugging Face Datasets: 667, latest observation ; 0 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Datasets | ant-intl/BizAgentBench | https://huggingface.co/datasets/ant-intl/BizAgentBench |