Skip to content
Yardstick
  1. Benchmarks
  2. Arena WebDev

Arena WebDev

Blind head-to-head votes on web apps that two anonymous models build from the same prompt.

CodingRun by Arena (formerly LMArena)Official leaderboard (opens in a new tab)

Top score
1,814Claude Opus 5.5
Median of field
1,61927 models scored
Data as of
Oct 7, 2026Arena leaderboard

Standings

Dots mark each rating on a shared scale from 1,200 to 1,850; ratings have no meaningful zero, so bar lengths would mislead.

  1. Rank 1
    Claude Opus 5.51,814

    Anthropic · $4 / $20New

  2. Rank 2
    GPT-6 Astra1,788

    OpenAI · $10 / $50New

  3. Rank 3
    Claude Sonnet 5.51,773

    Anthropic · $2 / $10New

  4. Rank 4
    GPT-6.1 Sol1,757

    OpenAI · $2 / $10New

  5. Rank 5
    Claude Fable 5.11,745

    Anthropic · $10 / $50New

  6. Rank 6
    Gemini 4 Argon1,678

    Google · $2 / $10NewPreview

  7. Rank 7
    Qwen3.8-Max1,672

    Alibaba · $2 / $6

  8. Rank 8
    Muse Spark 1.31,656

    Meta · $1.25 / $4.25New

  9. Rank 9
    Kimi K31,655

    Moonshot AI · $3 / $15Open weights

  10. Rank 10
    Grok 4.71,638

    SpaceXAI · $2 / $6New

  11. Rank 11
    Qwen3.8-Flash-Next1,632

    Alibaba · $0.15 / $0.47NewOpen weights

  12. Rank 12
    MiMo-V2.6-Pro1,630

    Xiaomi · $0.435 / $0.87NewOpen weights

  13. Rank 13
    GLM-5.31,622

    Z.ai · $1.40 / $4.40NewOpen weights

  14. Rank 14
    DeepSeek-V4.1-Flash1,619

    DeepSeek · $0.30 / $1.20NewOpen weights

  15. Rank 15
    GLM-5.3-Flash1,610

    Z.ai · $0.15 / $0.50NewOpen weights

  16. Rank 16
    Qwen3.8-27B1,592

    Alibaba · $0.50 / $3NewOpen weights

  17. Rank 17
    Gemini 3.8 Flash1,583

    Google · $0.75 / $3.75New

  18. Rank 18
    DeepSeek-V4-Pro1,582

    DeepSeek · $1.32 / $3.96NewOpen weights

  19. Rank 18
    GPT-6 Luna1,582

    OpenAI · $0.10 / $0.50New

  20. Rank 20
    Mistral Large 41,534

    Mistral AI · $1.36 / $4.18NewPreview

  21. Rank 21
    MiniMax M31,482

    MiniMax · $0.30 / $1.20Open weights

  22. Rank 22
    Kimi K2.7 Code1,473

    Moonshot AI · $0.95 / $4Open weights

  23. Rank 23
    Gemini 3.1 Pro1,447

    Google · $2 / $12Preview

  24. Rank 24
    Gemini 3.5 Flash-Lite1,440

    Google · $0.30 / $2.50

  25. Rank 25
    Gemma 4 31B1,365

    Google · Self-hostedOpen weights

  26. Rank 26
    Muse Glimmer 30B1,355

    Meta · Self-hostedNewOpen weights

  27. Rank 27
    Mistral Medium 3.51,263

    Mistral AI · $1.50 / $7.50Open weights

Not reported for Arena WebDev · 2

  • ·
    Claude Haiku 5.5—Not reported

    Anthropic · $0.10 / $0.50New

  • ·
    Mistral Small 4—Not reported

    Mistral AI · $0.15 / $0.60Open weights

What it measures

Which model people prefer when both are asked to build the same website or web app, including multi-step agentic builds.

How it is scored

Pairwise human votes are fitted to an Elo-style rating. A 100-point gap means the higher-rated model wins roughly two match-ups in three.

Read it with care

Preference is not correctness: voters judge what they can see and click. Ratings a few points apart are statistical ties, and scores Arena marks preliminary rest on few votes.

Other benchmarks

  • Artificial Analysis Intelligence Index
  • Epoch Capabilities Index
  • LiveBench
  • Terminal-Bench 4.0
  • SWE-Bench Pro (V2 Hard)
  • GDPval-AA
  • Vending-Bench 2
  • ARC-AGI-2
  • ARC-AGI-3
  • FrontierMath (Tiers 1–3)
  • MathArena
  • SimpleBench
  • Humanity's Last Exam (Diamond)
  • GPQA Diamond
  • Arena Vision
  • Arena Text
Yardstick

A plain reading of how today’s SI models compare. Scores are taken from each benchmark’s own leaderboard wherever one exists; anything a lab reported about its own model is marked.

Data as of Oct 8, 2026.

Explore

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Methodology & sources

Sources

  • Artificial Analysis (opens in a new tab)
  • Arena (opens in a new tab)
  • Epoch AI Benchmarking Hub (opens in a new tab)
  • ARC Prize (opens in a new tab)
  • Terminal-Bench (opens in a new tab)
  • Scale AI Labs (opens in a new tab)

Yardstick is an independent reference and is not affiliated with, sponsored by or endorsed by any lab listed. Product names and logos are trademarks of their respective owners and are used only to identify them. Benchmarks are imperfect proxies: check a model on your own task before you commit to it.

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs