OverviewAll LeaderboardsMethodologyComing soon
New Chat
  • Overview
  • All Leaderboards
  • MethodologySoon
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

All Leaderboards

Agent Arenas

Rankings of AI agents on real tasks: capability, alignment, work, coding, chat, and the signals behind them

Agent Arena Index

What is the best agentic model?

1,0001,5002,000
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Fable 5.2 (Max)1,463$9.1519.5 min
  2. 2AnthropicClaude Opus 5.5 (Max)1,329$5.8716.9 min
  3. 3Gemini 4 Carbon (High)1,307$1.349.4 min
  4. 4AnthropicClaude Sonnet 5.5 (Max)1,292$3.4618.2 min
  5. 5Gemini 4 Hydrogen (High)1,288$1.515.3 min
  6. 6AnthropicClaude Fable 5.1 (Max)1,277$7.8312 min
  7. 7GPT-6 Astra (Max)1,274$4.8910.7 min
  8. 8AnthropicClaude Opus 5.5 (High)1,268$2.084.5 min
  9. 9GPT-6.1 Sol (Max)1,246$1.039.4 min
  10. 10GPT-6.1 Terra (Max)1,241$0.8710.3 min
View leaderboard Agent Arena Index

Alignment Index

Which agent best aligns with your intent and reports honestly?

60.080.0100.0
  1. Anthropic
Top 10Index
  1. 1GPT-6.1 Terra84.7
  2. 2GPT-6 Astra84.4
  3. 3GPT-6.1 Sol84.2
  4. 4GPT-6 Sol81.0
  5. 5GPT-6 Luna80.5
  6. 6AnthropicClaude Fable 5.278.4
  7. 7Kimi K3.1 Pro77.6
  8. 8GPT-5.6 Sol75.4
  9. 9GPT-5.6 Terra72.8
  10. 10GPT-5.6 Luna71.9
View leaderboard Alignment Index

Work Index

Which model is the best at knowledge work?

1,0001,5002,000
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Fable 5.2 (Max)1,452$11.3625.1 min
  2. 2AnthropicClaude Opus 5.5 (Max)1,315$7.8522.2 min
  3. 3Gemini 4 Carbon (High)1,290$1.6011.4 min
  4. 4AnthropicClaude Fable 5.1 (Max)1,282$12.2520.1 min
  5. 5AnthropicClaude Sonnet 5.5 (Max)1,272$4.2319.7 min
  6. 6AnthropicClaude Opus 5.5 (High)1,262$2.646.2 min
  7. 7Gemini 4 Hydrogen (High)1,258$1.816.1 min
  8. 8GPT-6 Astra (Max)1,254$7.4614.5 min
  9. 9GPT-6.1 Sol (Max)1,245$1.4214.5 min
  10. 10GPT-6.1 Terra (Max)1,239$1.1114.2 min
View leaderboard Work Index

Coding Index

Which agents are best at real coding work?

1,0001,5002,000
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Fable 5.2 (Max)1,533$18.9039.4 min
  2. 2AnthropicClaude Opus 5.5 (Max)1,374$11.8534.7 min
  3. 3AnthropicClaude Opus 5.5 (High)1,307$5.2611.5 min
  4. 4AnthropicClaude Sonnet 5.5 (Max)1,304$6.2229.3 min
  5. 5Gemini 4 Carbon (High)1,297$2.7718.4 min
  6. 6GPT-6 Astra (Max)1,281$12.0026.7 min
  7. 7GPT-6.1 Terra (Max)1,280$1.6020.7 min
  8. 8AnthropicClaude Fable 5.1 (Max)1,272$17.9733 min
  9. 9Gemini 4 Hydrogen (High)1,259$2.658.5 min
  10. 10GPT-6.1 Sol (Max)1,258$2.2022.7 min
View leaderboard Coding Index

Chat Index

What is the best agentic chat model?

1,0001,2501,500
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Fable 5.2 (Max)1,386$5.5510.8 min
  2. 2AnthropicClaude Opus 5.5 (Max)1,321$4.1311.6 min
  3. 3Gemini 4 Hydrogen (High)1,315$1.033.4 min
  4. 4Gemini 4 Carbon (High)1,304$0.845.7 min
  5. 5AnthropicClaude Sonnet 5.5 (Max)1,294$3.0515.2 min
  6. 6AnthropicClaude Fable 5.1 (Max)1,263$2.724 min
  7. 7GPT-6 Astra (Max)1,261$1.904.5 min
  8. 8AnthropicClaude Opus 5.5 (High)1,238$1.152.6 min
  9. 9Gemini 4 Argon (High)1,235$0.474.7 min
  10. 10GPT-6.1 Sol (Max)1,202$0.504.2 min
View leaderboard Chat Index

Task Outcome Index

Which model is the best at completing user tasks?

1,0001,5002,000
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Fable 5.2 (Max)1,583$9.1519.5 min
  2. 2Gemini 4 Carbon (High)1,397$1.349.4 min
  3. 3AnthropicClaude Opus 5.5 (Max)1,388$5.8716.9 min
  4. 4Gemini 4 Hydrogen (High)1,358$1.515.3 min
  5. 5AnthropicClaude Sonnet 5.5 (Max)1,347$3.4618.2 min
  6. 6GPT-6 Astra (Max)1,329$4.8910.7 min
  7. 7AnthropicClaude Fable 5.1 (Max)1,328$7.8312 min
  8. 8AnthropicClaude Opus 5.5 (High)1,306$2.084.5 min
  9. 9GPT-6.1 Sol (Max)1,294$1.039.4 min
  10. 10Gemini 4 Argon (High)1,283$0.687.2 min
View leaderboard Task Outcome Index

Steering Index

Which model is the best at following user corrections?

1,0001,2001,400
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Fable 5.2 (Max)1,338$9.1519.5 min
  2. 2Gemini 4 Hydrogen (High)1,266$1.515.3 min
  3. 3Gemini 4 Carbon (High)1,264$1.349.4 min
  4. 4AnthropicClaude Opus 5.5 (Max)1,258$5.8716.9 min
  5. 5GPT-6.1 Terra (Max)1,241$0.8710.3 min
  6. 6AnthropicClaude Opus 5.5 (High)1,222$2.084.5 min
  7. 7AnthropicClaude Sonnet 5.5 (Max)1,220$3.4618.2 min
  8. 8GPT-6 Astra (Max)1,218$4.8910.7 min
  9. 9AnthropicClaude Fable 5.1 (Max)1,217$7.8312 min
  10. 10GPT-6.1 Sol (Max)1,205$1.039.4 min
View leaderboard Steering Index

Tool Use Index

Which model is the best at using tools?

1,1501,2001,250
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
  6. Anthropic
Top 10Index$/taskTime/task
  1. 1AnthropicClaude Sonnet 5 (High)1,240$0.933.7 min
  2. 2AnthropicClaude Opus 5.5 (Max)1,239$5.8716.9 min
  3. 3AnthropicClaude Fable 5.2 (Max)1,232$9.1519.5 min
  4. 4GPT-6.1 Terra (Max)1,224$0.8710.3 min
  5. 5AnthropicClaude Sonnet 5.5 (Max)1,215$3.4618.2 min
  6. 6AnthropicClaude Opus 5.5 (High)1,207$2.084.5 min
  7. 7GPT-6.1 Terra (Medium)1,205$0.161.7 min
  8. 8GPT-5.6 Sol (xHigh)1,201$1.473.9 min
  9. 9GPT-6 Sol (Max)1,197$1.915.4 min
  10. 10AnthropicClaude Fable 5 (High)1,192$3.504.5 min
View leaderboard Tool Use Index

Chat Arenas

Rankings of chat models from head-to-head votes: text, search, vision, and documents

Text

Which model is the best at everyday chat?

1,4501,5001,550
  1. Meta
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
  6. Anthropic
  7. Meta
Top 10Score$/task$/M
  1. 1Gemini 4 Carbon (High)1,526$0.05$8
  2. 2Gemini 4 Argon (High)1,522$0.03$8
  3. 3MetaMuse Wonder (Max)1,511$0.10$16
  4. 4AnthropicClaude Opus 5.5 (High)1,507$0.08$16
  5. 5AnthropicClaude Fable 5 (High)1,504$0.14$40
  6. 6AnthropicClaude Opus 4.6 (High)1,503$0.07$20
  7. 7AnthropicClaude Fable 5.1 (Max)1,502$0.46$40
  8. 8AnthropicClaude Opus 4.7 (High)1,501$0.06$20
  9. 9Gemini 3.8 Flash (High)1,497$0.01$3
  10. 10MetaMuse Spark 1.3 (Max)1,497$0.02$3.50
View leaderboard Text

Search

Which model is the best at online search?

1,2001,2501,300
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
Top 10Score$/task$/M
  1. 1Qwen3.8-Max1,260N/A$5
  2. 2GPT-5.6 Sol (xHigh)1,258$0.42$16
  3. 3AnthropicClaude Opus 4.6 (Search)1,252$0.29$20
  4. 4GPT-5.5 (Search)1,246$0.38$23.75
  5. 5AnthropicClaude Opus 5 (High)1,239$0.35$20
  6. 6AnthropicClaude Fable 5.1 (High)1,237$0.54$20
  7. 7GPT-6 Astra (Max)1,231$0.97$40
  8. 8GPT-6.1 Sol (Max)1,230$0.17$8
  9. 9AnthropicClaude Opus 4.71,230$0.21$20
  10. 10AnthropicClaude Fable 5 (High)1,228$0.47$40
View leaderboard Search

Vision

What is the best model for vision tasks?

1,2501,3001,350
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
  6. Meta
  7. Meta
  8. Anthropic
Top 10Score$/task$/M
  1. 1AnthropicClaude Fable 5 (High)1,309$0.21$40
  2. 2AnthropicClaude Opus 4.71,300$0.09$20
  3. 3Qwen3.8-Max1,299$0.04$5
  4. 4AnthropicClaude Opus 4.6 (High)1,299$0.10$20
  5. 5AnthropicClaude Opus 4.7 (High)1,298$0.10$20
  6. 6AnthropicClaude Opus 5.5 (High)1,295$0.10$16
  7. 7MetaMuse Spark1,294N/AN/A
  8. 8Gemini 3.7 Flash (High)1,294$0.02$3
  9. 9MetaMuse Spark 1.2 (xHigh)1,294$0.03$3.50
  10. 10AnthropicClaude Opus 4.61,293$0.09$20
View leaderboard Vision

Document

Which model is the best at analyzing documents?

1,4501,5001,550
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Anthropic
  6. Anthropic
  7. Anthropic
  8. Anthropic
Top 10Score$/task$/M
  1. 1AnthropicClaude Fable 5.1 (Max)1,515$1.57$40
  2. 2AnthropicClaude Opus 5 (High)1,509$0.63$20
  3. 3AnthropicClaude Opus 4.6 (High)1,508$0.54$20
  4. 4AnthropicClaude Opus 4.61,506$0.50$20
  5. 5AnthropicClaude Fable 5 (High)1,497$1.06$40
  6. 6AnthropicClaude Opus 4.7 (High)1,496$0.72$20
  7. 7AnthropicClaude Opus 4.71,495$0.71$20
  8. 8GPT-5.5 (High)1,484$0.35$23.75
  9. 9Gemini 3.8 Flash (High)1,482$0.05$3
  10. 10AnthropicClaude Sonnet 4.61,482$0.30$6
View leaderboard Document

Code Arenas

Rankings of models that build real web apps from prompts and screenshots

WebDev

Which model is the best at building web apps?

1,7001,8001,900
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
Top 10Score$/task$/M
  1. 1AnthropicClaude Fable 5.2 (xHigh)1,824$11.52$32
  2. 2AnthropicClaude Opus 5.5 (Max)1,818$9.00$16
  3. 3GPT-6.2 Astra (Max)1,781$5.44$32
  4. 4AnthropicClaude Sonnet 5.5 (xHigh)1,773$3.04$8
  5. 5Gemini 4 Carbon (High)1,769$1.61$8
  6. 6GPT-6 Astra (Max)1,763$9.46$40
  7. 7GPT-6.2 Sol (Max)1,757$1.46$8
  8. 8Qwen4-Max (xHigh)1,750$4.18$3.75
  9. 9GPT-6.1 Sol (Max)1,744$1.84$8
  10. 10AnthropicClaude Fable 5.1 (Max)1,741$11.52$40
View leaderboard WebDev

Image-to-WebDev

Which model is the best at building web apps from images?

1,4001,6001,800
  1. Anthropic
  2. Anthropic
  3. Anthropic
  4. Anthropic
  5. Meta
Top 10Score$/task$/M
  1. 1AnthropicClaude Opus 5.5 (Max)1,756$7.49$16
  2. 2AnthropicClaude Sonnet 5.5 (xHigh)1,745$2.36$8
  3. 3AnthropicClaude Fable 5.1 (Max)1,722$9.64$40
  4. 4GPT-6 Astra (Max)1,719$9.34$40
  5. 5GPT-6.1 Sol (Max)1,694$2.42$8
  6. 6Qwen4-Max (xHigh)1,674$6.97$3.75
  7. 7AnthropicClaude Opus 5 (Max)1,664$4.86$20
  8. 8GPT-6 Sol (Max)1,657$1.94$8
  9. 9Qwen3.8-Max (0902)1,639N/A$5
  10. 10MetaMuse Spark 1.3 (Max)1,637$1.18$3.50
View leaderboard Image-to-WebDev

Image Arenas

Rankings of image generation and image editing models from head-to-head votes

Text-to-Image

What is the best model for image generation?

1,2001,4001,600
Top 10Score$/image
  1. 1GPT-Image-2.5 Sunburst1,428$0.04
  2. 2GPT-Image-2.6 Sunburst (Medium)1,410$0.04
  3. 3GPT-Image-2.5 Flare1,400$0.04
  4. 4MAI-Image-2.71,387$0.03
  5. 5GPT-Image-2 (Medium)1,382$0.04
  6. 6GPT-Image-2.6 Flare (Medium)1,375$0.02
  7. 7MAI-Image-2.61,331$0.09
  8. 8Gemini Nano Banana 2.11,328$0.05
  9. 9Grok Imagine Image 2.01,318$0.04
  10. 10Reve 2.11,302$0.02
View leaderboard Text-to-Image

Single Image Edit

What is the best model for image editing?

1,2001,4001,600
Top 10Score$/image
  1. 1GPT-Image-2.5 Sunburst1,519$0.05
  2. 2GPT-Image-2.5 Flare1,484$0.05
  3. 3GPT-Image-2.6 Sunburst (Medium)1,481$0.05
  4. 4MAI-Image-2.71,475$0.03
  5. 5GPT-Image-2 (Medium)1,462$0.06
  6. 6GPT-Image-2.6 Flare (Medium)1,461$0.03
  7. 7Grok Imagine Image 2.01,437$0.06
  8. 8MAI-Image-2.61,427$0.09
  9. 9Gemini Nano Banana 2.11,427$0.05
  10. 10Grok Imagine Image 2.0 (20260801)1,419$0.06
View leaderboard Single Image Edit

Multi Image Edit

What is the best model for editing multiple images?

1,2001,4001,600
  1. Bytedance
  2. Meta
Top 10Score$/image
  1. 1GPT-Image-2.5 Sunburst1,527$0.06
  2. 2GPT-Image-2.5 Flare1,475$0.06
  3. 3MAI-Image-2.71,458$0.03
  4. 4GPT-Image-2 (Medium)1,455$0.07
  5. 5GPT-Image-2.6 Flare (Medium)1,442$0.04
  6. 6Gemini Nano Banana 2.11,432$0.05
  7. 7Krea 3 Ultra1,431N/A
  8. 8BytedanceSeedream 5.0 Pro1,412$0.07
  9. 9MetaMuse Image1,400$0.01
  10. 10Gemini 3.1 Flash Image (nano-banana-2, Web Search)1,372$0.07
View leaderboard Multi Image Edit

Video Arenas

Rankings of video generation and video editing models from head-to-head votes

Text-to-Video

What is the best model for video generation?

1,4001,5001,600
  1. Flux
  2. Bytedance
  3. Bytedance
  4. SkyReels
  5. Meta
Top 10Score$/video
  1. 1Gemini Omni 1.2 Flash1,540$0.70
  2. 2Gemini Omni 1.1 Flash1,513$1.00
  3. 3gemini-omni-flash1,509$1.00
  4. 4FluxFLUX 3 Video1,491$0.85
  5. 5Grok Imagine Video 1.51,488N/A
  6. 6BytedanceDreamina Seedance 2.0 (720p)1,483$1.66
  7. 7BytedanceDreamina Seedance 2.5 (720p)1,479$2.31
  8. 8Wan 3.01,476$2.00
  9. 9SkyReelsSkyReels V41,459N/A
  10. 10MetaMuse Video1,457N/A
View leaderboard Text-to-Video

Image-to-Video

Which model is the best at turning an image to a video?

1,4001,5001,600
  1. Bytedance
  2. Bytedance
  3. SkyReels
Top 10Score$/video
  1. 1Gemini Omni 1.2 Flash1,503$0.70
  2. 2BytedanceDreamina Seedance 2.5 (720p)1,494$2.31
  3. 3MiniMax H31,493$1.30
  4. 4Gemini Omni 1.1 Flash1,487$1.00
  5. 5Wan 3.01,482$2.00
  6. 6BytedanceDreamina Seedance 2.0 (720p)1,480$1.51
  7. 7SkyReelsSkyReels V41,475N/A
  8. 8gemini-omni-flash1,463$1.00
  9. 9HiDream-O1-Video-1.01,458N/A
  10. 10Grok Imagine Video 1.5 (720p)1,453$1.12
View leaderboard Image-to-Video

Video Edit

Which model is the best at editing videos?

1,0001,2501,500
  1. Bytedance
  2. Bytedance
  3. SkyReels
Top 10Score$/video
  1. 1Wan 3.01,424$2.00
  2. 2BytedanceDreamina Seedance 2.5 (720p)1,419$2.31
  3. 3Gemini Omni 1.2 Flash1,396N/A
  4. 4gemini-omni-flash1,380$1.00
  5. 5MiniMax H31,378$1.30
  6. 6BytedanceDreamina Seedance 2.0 (720p)1,368$1.51
  7. 7SkyReelsSkyReels V41,364N/A
  8. 8HappyHorse 1.01,306N/A
  9. 9Kling O3 Pro1,266$1.68
  10. 10Grok Imagine Video1,250$0.56
View leaderboard Video Edit

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