AgentBench and LLM-Agent-Benchmark-List
About AgentBench
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
This project helps developers and researchers evaluate how well large language models (LLMs) can act as autonomous 'agents' in various real-world scenarios. It takes an LLM as input and runs it through a standardized set of tasks, like interacting with an operating system, using a database, or shopping online. The output is a performance score, showing how effectively the LLM completes these multi-step, interactive tasks.
About LLM-Agent-Benchmark-List
zhangxjohn/LLM-Agent-Benchmark-List
A banchmark list for evaluation of large language models.
This resource helps AI researchers and developers understand and compare how well Large Language Models (LLMs) and LLM-powered agents perform on different tasks. It provides a structured list of benchmarks, including papers and project pages, allowing you to select appropriate evaluation methods for specific LLM applications. This is for anyone building, researching, or deploying LLMs and agent systems who needs to rigorously assess their capabilities.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work