Arena

Community-voting LLM leaderboard (formerly LMArena/Chatbot Arena) that now sells agent-evaluation analytics and a real-world alignment benchmark to AI labs.

Arena · Evaluation, observability, and MLOps tooling · product

Published in Feed

Overview

Arena, the community platform formerly known as LMArena/Chatbot Arena (rebranded January 28, 2026), pairs free community model rankings with a paid analytics product, AI Evaluations, for AI labs and enterprises. On October 8, 2026 it announced a $200 million Series B at a $3.1 billion valuation co-led by Lightspeed Venture Partners and Khosla Ventures, alongside the Arena Alignment Index, a benchmark built from more than 90,000 real-world agent sessions across 27 models that scores agent behavioral reliability rather than raw capability.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Free community leaderboard: users submit prompts/coding tasks and vote between model responses
  • AI Evaluations: paid performance analytics for AI labs and enterprises based on community feedback
  • Arena Alignment Index: scores three behavioral signals - Unauthorized Action, False Attribution, and Deceptive Completion - across 27 models and 90,000+ agent sessions
  • Scoring methodology for the Alignment Index uses rubrics, an AI judge, and human review, but exact scoring weights are not publicly disclosed

Use cases

  • Public, crowd-sourced comparison of LLM/chatbot quality
  • Enterprise/lab procurement decisions using paid performance analytics
  • Benchmarking agent behavioral reliability and compliance risk before production deployment

Pricing

Community leaderboard is free; AI Evaluations is a paid product for labs/enterprises (pricing not publicly disclosed). Company has exceeded $100M in annualized revenue.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
8 Oct 2026
Record updated
13 Oct 2026
Record last checked
13 Oct 2026

Explore the Feed

Other entries filed under evaluation, observability, and mlops tooling; inclusion does not imply equivalent features.

Browse the Feed