agbenchmark

Tools & Infrastructure

AGBenchmark is a standardized evaluation framework for measuring the performance of autonomous AI agents across diverse tasks, originally developed by the AutoGPT team.

🌐 Visit website ↗

🔗 Similar tools

ToolBench ★ 5.7k

ToolBench is an open platform for training, serving, and evaluating large language models …
BrowserGym ★ 1.3k

BrowserGym provides a Gym-style benchmark and environment toolkit for evaluating web agent…
ClawBench ★ 649

ClawBench is a browser-agent benchmark consisting of 153 everyday tasks across 144 live pr…
Multi-SWE-bench ★ 362

Multi-SWE-bench is a multi-language extension of SWE-bench that evaluates software enginee…
Whisper v3 (local) ★ 108.5k

Whisper v3 is a local, open-source automatic speech recognition model trained on 680,000 h…

Voice & Multimodal
Harbor ★ 5.0k

Harbor is an Apache-2.0 framework, developed by Stanford and the Laude Institute, for eval…