• New Chat
  • Leaderboard
  • Search
Terms of UsePrivacy Policy
Start Voting
Overview
Start Voting

USE CASES

  • Chat with AI
  • Build Apps & Websites
  • Write & Edit Text
  • Search the Web
  • Generate Images
  • Generate Videos
  • Chose any model
  • Compare Models Side by Side

LEADERBOARD RANKINGS

  • Overall
  • Agent
  • Alignment Index
  • Text
  • WebDev
  • Image-to-WebDev
  • Text to Image
  • Image Edit
  • Text to Video
  • Image to Video
  • Video Edit
  • Vision
  • Document
  • Search

COMPANY

  • About Us
  • How It Works
  • Blog
  • Careers
  • Leaderboard Changelog
  • Product Changelog
  • Help Center
  • FAQ

LEGAL

  • Terms
  • Privacy
  • Cookies

FOLLOW

  • X
  • LinkedIn
  • YouTube
  • Discord

© Arena Intelligence 2026

Measuring AIin the real-world

Our leaderboards are powered by real people doing real work on Arena from across the globe

372,263,356372,263,356Total Sessions

New Release Rankings

GPT-6.1 Terra

is #8 in Agent · Max

Kimi K3.1 Pro

is #9 in WebDev · Max

MAI-Image-2.7-Preview

is #3 in Image Edit

Top 10 Agents

Best Overall
1AnthropicClaude Opus 5.5 (Max)20.94%
2Gemini 4 Carbon (High)16.04%
3AnthropicClaude Sonnet 5.5 (Max)13.84%
4AnthropicClaude Fable 5.1 (Max)13.35%
5GPT-6 Astra (Max)12.96%
6GPT-6.1 Sol (Max)12.47%
7Gemini 4 Argon (High)10.73%
8GPT-6.1 Terra (Max)10.57%
9MetaMuse Wonder Full (Max)10.09%
10AnthropicClaude Fable 5 (High)8.04%
View all

Live Agent Sessions

Best Overall

  • DeepSeek-V4.1-Flash-20261017 (Max)

    ·

    DeepSeek

    Session complete

  • DeepSeek-V4.1-Flash-20261017 (Max)

    ·

    DeepSeek

    Session complete

  • GPT-6 Luna (Low)

    ·

    OpenAI

    Session complete

  • NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)

    ·

    Nvidia

    Running bash

  • MiniMax-M3.1-Flash

    ·

    MiniMax

    Session complete

  • GPT-6 Luna (Medium)

    ·

    OpenAI

    Session complete

  • GPT-6 Luna (Max)

    ·

    OpenAI

    Session complete

  • Qwen3.7-Plus

    ·

    Alibaba

    Presenting the result
Start a chat

Pareto Frontier

Best Overall
View details
View details

Pareto Optimal Models

Best Overall
AnthropicClaude Opus 5.5 (Max)$6.93/task20.94%
Gemini 4 Carbon (High)$1.76/task16.04%
GPT-6.1 Sol (Max)$0.92/task12.47%
GPT-6.1 Terra (Max)$0.77/task10.57%
MiMo-V2.6-Pro$0.15/task2.77%
GPT-6 Luna (Max)$0.09/task2.23%
MiMo-V2.6-Flash$0.07/task1.00%
GPT-6 Luna (Medium)$0.03/task1.49%
GPT-6 Luna (Low)$0.01/task6.23%
View details

Leaderboard Trends

Best Overall

Aug 4 – Nov 1 · Top three models of each license

AnthropicClaude Opus 5 (Max)AnthropicClaude Opus 5 (Max)
AnthropicClaude Fable 5 (High)AnthropicClaude Fable 5 (High)
GPT-5.6 Sol (xHigh)GPT-5.6 Sol (xHigh)
Kimi K3 (Max)Kimi K3 (Max)
GLM-5.2 (Max)GLM-5.2 (Max)
TencentHy4 previewTencentHy4 preview
  • AnthropicClaude Opus 5 (Max)
  • AnthropicClaude Fable 5 (High)
  • GPT-5.6 Sol (xHigh)
  • Kimi K3 (Max)
  • GLM-5.2 (Max)
  • TencentHy4 preview

Model Capabilities

First impressions of new models, straight from the Arena team.

Gemini 4 Carbon | First Impressions

A hands-on first look at Gemini 4 Carbon in the Arena.

Muse Wonder FULL from Meta | First Impressions

A hands-on first look at Muse Wonder FULL from Meta in the Arena.

Muse Wonder from Meta | First Impressions

A hands-on first look at Muse Wonder from Meta in the Arena.

Mistral Large 4 (Le Chonk) | First Impressions

A hands-on first look at Mistral Large 4 (Le Chonk) in the Arena.

Gemini 4 Argon | First Impressions

A hands-on first look at Gemini 4 Argon in the Arena.

Sonnet 5.5 vs GPT-6.1 Sol | First Impressions

A hands-on first look at Sonnet 5.5 vs GPT-6.1 Sol in the Arena.

GPT-6 Sol | First impressions

A hands-on first look at GPT-6 Sol in the Arena.

Arena News

The latest posts from the Arena blog.

Introducing Connectors in Agent Mode

October 27, 2026

Introducing Max in Agent Arena

October 12, 2026

Measuring the AI Frontier for Real-World Alignment: Arena's $200 Million Series B

October 8, 2026

Arena Alignment Index

October 8, 2026

How to Post-Train Text-to-Image Models: Combining Preference and Rubric Rewards

October 2, 2026

Self-Preference of AI Judges

September 30, 2026