EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios

EVA-Bench Data 2.0 is an expanded benchmark dataset containing tools and scenarios across 3 domains, featuring 121 tools and 213 test scenarios for evaluating AI agent performance. This dataset enables comprehensive assessment of how well language models can understand and utilize diverse tools in practical applications. The benchmark is designed to advance evaluation standards for AI agents' tool-use capabilities across multiple domains.

Source: Hugging Face | 2026-06-04