LMArena (formerly Chatbot Arena)

Tools & Infrastructure

LMArena is a crowdsourced LLM benchmark that ranks models based on human preference voting, rebranded from LMSYS in 2025. It provides an open platform for developers to compare AI assistant performance through real-time pairwise comparisons.

🌐 Visit website ↗

🔗 Similar tools

Arena (formerly LMArena / Chatbot Arena)

Arena (formerly LMArena/Chatbot Arena) is a crowdsourced AI benchmark that ranks models vi…
JetBrains Kotlin Benchmark

JetBrains Kotlin Benchmark is a public benchmark from JetBrains that evaluates AI coding a…
Ntfy ★ 34.0k

Ntfy sends real-time notifications to phones and desktops through a simple HTTP API, enabl…
Discord.py ★ 16.2k

Discord.py is a Python library that enables agents to interact with Discord channels and s…
BrowserGym ★ 1.3k

BrowserGym provides a Gym-style benchmark and environment toolkit for evaluating web agent…
langtrace ★ 1.2k

Langtrace is an open-source, OpenTelemetry-based observability tool for LLM applications t…