Skip to content

AgentBench

AgentsEnglishBenchmark

Created by Tsinghua University (Liu et al.) at 2023, the AgentBench is a agents benchmark dataset in English containing 1,000+ records in JSON format.

📊 This dataset is used as an LLM benchmark. See model leaderboards →

Details

Task
Agents
Language
English
Format
JSON
Rows / instances
1,000+
Creator
Tsinghua University (Liu et al.)
Year
2023
Download Paper

FAQ