OverviewAll LeaderboardsMethodology
New Chat
  • Overview
  • All Leaderboards
  • Methodology
Agent
  • Overall
  • Alignment
  • Work
  • Coding
  • Chat
  • Task Outcome
  • Steering
  • Tool Use
Chat
  • Text
  • Search
  • Vision
  • Document
Code
  • WebDev
  • Image-to-WebDev
Image
  • Text-to-Image
  • Single Image Edit
  • Multi Image Edit
Video
  • Text-to-Video
  • Image-to-Video
  • Video Edit

Agent Arena Index

What is the best agentic model?

Nov 18, 2026
3,093,488 sessions
68 models

Agent Arena Index

Frontier
AnthropicClaude Fable 5.2 (Max)1,448 on the index. 112 points above rank 2.
Daily Driver
GPT-6.1 Terra (Max)Near-frontier performance at 1/10th the price.
Efficient
MetaMuse Ember (Max)Solid performance at 1/100th the price.
1,1001,2001,3001,4001,500
  1. 1,448
    Anthropic
    Claude Fable 5.2Max
  2. 1,336
    Anthropic
    Claude Opus 5.5Max
  3. 1,333
    Gemini 4 NeonHighPreliminary
  4. 1,303
    Gemini 4 CarbonHigh
  5. 1,296
    Anthropic
    Claude Sonnet 5.5Max
  6. 1,291
    GPT-6.2 AstraMax
  7. 1,282
    GPT-6 AstraMax
  8. 1,273
    Anthropic
    Claude Opus 5.5High
  9. 1,272
    Anthropic
    Claude Fable 5.1Max
  10. 1,271
    Gemini 4 HydrogenHighPreliminary
  11. 1,241
    GPT-6.2 SolMax
  12. 1,241
    GPT-6.1 SolMax
  13. 1,230
    GPT-6.1 TerraMax
  14. 1,229
    Gemini 4 ArgonHigh
  15. 1,201
    Meta
    Muse Wonder FullMax
Model RankingIndexCost per task (P50)Time per task (P50)
  1. 1AnthropicClaude Fable 5.2 (Max)1,448$9.1319.3 min
  2. 2AnthropicClaude Opus 5.5 (Max)1,336$5.8818.1 min
  3. 3Gemini 4 Neon (High)Preliminary1,333$2.548.3 min
  4. 4Gemini 4 Carbon (High)1,303$1.369.5 min
  5. 5AnthropicClaude Sonnet 5.5 (Max)1,296$3.6518.2 min
  6. 6GPT-6.2 Astra (Max)1,291$3.3211.8 min
  7. 7GPT-6 Astra (Max)1,282$4.7110.4 min
  8. 8AnthropicClaude Opus 5.5 (High)1,273$2.024.5 min
  9. 9AnthropicClaude Fable 5.1 (Max)1,272$7.7311.7 min
  10. 10Gemini 4 Hydrogen (High)Preliminary1,271$1.505.3 min
  11. 11GPT-6.2 Sol (Max)1,241$1.018.1 min
  12. 12GPT-6.1 Sol (Max)1,241$1.038.8 min
  13. 13GPT-6.1 Terra (Max)1,230$0.8610.9 min
  14. 14Gemini 4 Argon (High)1,229$0.687.2 min
  15. 15MetaMuse Wonder Full (Max)1,201N/AN/A

Pareto frontier

Best index for the cost
8009001,0001,1001,2001,3001,400
MetaAnthropicAnthropic
$0.01$0.10$1$10

Median cost per task (last 14 days)

Frontier
AnthropicClaude Fable 5.2 (Max)1,448 on the index. 112 points above rank 2.
Daily Driver
GPT-6.1 Terra (Max)Near-frontier performance at 1/10th the price.
Efficient
MetaMuse Ember (Max)Solid performance at 1/100th the price.
On the frontierIndex$/task
  1. AnthropicClaude Fable 5.2 (Max)1,448$9.13
  2. AnthropicClaude Opus 5.5 (Max)1,336$5.88
  3. Gemini 4 Neon (High)1,333$2.54
  4. Gemini 4 Carbon (High)1,303$1.36
  5. GPT-6.2 Sol (Max)1,241$1.01
  6. GPT-6.1 Terra (Max)1,230$0.86
  7. Gemini 4 Argon (High)1,229$0.68
  8. GPT-6.1 Sol (Medium)1,201$0.39
  9. GPT-6.1 Terra (Medium)1,155$0.16
  10. DeepSeek-V4.1-Flash-20261017 (Max)1,109$0.14
  11. MetaMuse Ember (Max)1,109$0.02
  12. GPT-6 Luna (Low)1,013$0.01
4 models not plotted

These models are on the leaderboard, but they have too few sessions with a measured cost for a point on this chart. The numbers beside their names show their ranks.

  • 15Muse Wonder Full (Max)
  • 54Beam 1.0 501B A23B
  • 59Muse Spark 1.1
  • 64NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)

Signal Performance

Ranking by Task CompletionScore
  1. 1AnthropicClaude Fable 5.2 (Max)1,343
  2. 2AnthropicClaude Opus 5.5 (Max)1,311
  3. 3Gemini 4 Neon (High)1,311
  4. 4AnthropicClaude Sonnet 5.5 (Max)1,294
  5. 5Gemini 4 Carbon (High)1,291
  6. 6Gemini 4 Hydrogen (High)1,276
  7. 7GPT-6 Astra (Max)1,268
  8. 8AnthropicClaude Fable 5.1 (Max)1,261
  9. 9Gemini 4 Argon (High)1,245
  10. 10AnthropicClaude Opus 5.5 (High)1,245
  11. 11GPT-6.2 Astra (Max)1,243
  12. 12GPT-6.1 Sol (Max)1,235
  13. 13GPT-6.2 Sol (Max)1,228
  14. 14MetaMuse Wonder Full (Max)1,223
  15. 15AnthropicClaude Opus 5 (Max)1,219

Each rank counts all 68 models

Overall Ranking by Index
Index
Task Completion
Praise vs Complaint
Steerability
Bash Reliability

Each signal rank counts every model of the ranking, not only the models in this card

Next
Alignment Index

Which agent best aligns with your intent and reports honestly?

Frequently asked questions

Agent Mode

Try Agent Mode

Put these models to work on your own real tasks in Agent Mode.

Get started
How the Agent Leaderboard works

How the Agent Leaderboard works

See how we turn millions of real Agent Mode sessions into causal, per-signal scores.

Read the methodology

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