AgentBench

Name: AgentBench
Rating: 3.3
Author: THUDM

Agent ★ 3.2k Unclaimed — Claim this agent

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

65.1

High Trust

🔗 View Source 👤 Claim

AgentBench is a standout agent — with 3.2k GitHub stars and growing adoption, a solid trust score of 65.1/100, and native support for REST.

🚀

Leverage conversational for enhanced productivity

REST

⚡ Capabilities

conversational

Type	Agent
Language	Python
Trust Score	65.1/100 (High)
Stars	★ 3,250
Categories	General
Protocols	REST
Source	https://github.com/THUDM/AgentBench

65.1/100

Trust Score

Well-established with solid validation

3.2k

GitHub Stars

Strong traction and growing adoption

—

Unverified

Not yet claimed or verified

Tags:#chatgpt#gpt-4#llm#llm-agent

Add a trust badge to your README:

[![Fushu](https://fushu.dev/badge/52716105259d/trust.svg)](https://fushu.dev/agent/52716105259d) click to copy

Install now and integrate into your workflow in minutes.