+1 (415) 347-6981Get started
Fixed prices · You own the code · Proposal in 24h hello@startrise.io →
Engineering discipline — email

HTML Email

30 models built this brief single-shot. Grok 4.6 leads at 87.6. 28 of 30 builds carry a blind human rating. 5 split the judge panel.

GitHub repo ↗
↗
  1. Grok 4.6 xAI · Aug 2026
    87.6
    100 gates83 panel85 human
    Open live ↗
  2. Claude Opus 5 Anthropic · Jul 2026
    84.3
    100 gates85 panel70 human
    Open live ↗
  3. Claude Opus 5.5 Anthropic · Oct 2026
    84.3
    100 gates85 panel70 human
    Open live ↗
  4. Grok 4.7 xAI · Oct 2026
    82.8
    100 gates85 panel65 human
    Open live ↗
  5. Claude Sonnet 5.5 (high) Anthropic · Oct 2026
    82.8
    100 gates85 panel65 human
    Open live ↗
  6. Claude Fable 5.1 Anthropic · Oct 2026
    81.6
    100 gates83 panel65 human
    Open live ↗
  7. Claude Sonnet 5.5 Anthropic · Oct 2026
    81.6
    100 gates83 panel65 human
    Open live ↗
  8. GPT-5.6 Sol OpenAI · Jul 2026
    80.5
    100 gates80 panel65 human
    Open live ↗
  9. GPT-6 Astra OpenAI · Oct 2026
    80.5
    100 gates80 panel65 human
    Open live ↗
  10. GPT-6.1 Sol OpenAI · Oct 2026
    80.5
    100 gates80 panel65 human
    Open live ↗
  11. GPT-6 Luna OpenAI · Oct 2026
    80.5
    100 gates80 panel65 human
    Open live ↗
  12. DeepSeek V4.1 Flash DeepSeek · Oct 2026
    80.5
    100 gates80 panel65 human
    Open live ↗
  13. Claude Opus 5.5 (high) Anthropic · Oct 2026
    79.8
    100 gates85 panel55 human
    Open live ↗
  14. Kimi K3 Moonshot · Jul 2026
    78.6
    100 gates83 panel55 human
    Open live ↗
  15. Gemini 3.8 Flash Google · Oct 2026 · split panel
    78.6
    100 gates73 panel70 human
    Open live ↗
  16. GLM 5.2 Z.ai · Jul 2026 · split panel
    77.5
    100 gates65 panel- human
    Open live ↗
  17. Muse Spark 1.2 Meta · Aug 2026
    76.0
    100 gates70 panel65 human
    Open live ↗
  18. Muse Spark 1.3 Meta · Oct 2026
    76.0
    100 gates80 panel50 human
    Open live ↗
  19. GLM 5.3 Z.ai · Oct 2026 · split panel
    74.9
    100 gates68 panel65 human
    Open live ↗
  20. Qwen 3.8 Max 0902 Alibaba · Oct 2026
    73.8
    100 gates75 panel50 human
    Open live ↗
  21. Qwen 3.8 Max Alibaba · Aug 2026
    73.4
    100 gates68 panel60 human
    Open live ↗
  22. DeepSeek V4 Pro 0813 DeepSeek · Oct 2026
    73.0
    100 gates70 panel55 human
    Open live ↗
  23. Grok 4.5 xAI · Jul 2026
    72.3
    100 gates75 panel45 human
    Open live ↗
  24. Claude Sonnet 5 Anthropic · Jul 2026 · split panel
    71.9
    100 gates68 panel55 human
    Open live ↗
  25. Claude Fable 5 Anthropic · Jul 2026 · split panel
    71.5
    100 gates80 panel35 human
    Open live ↗
  26. GPT-5.6 Terra OpenAI · Jul 2026
    70.8
    100 gates65 panel55 human
    Open live ↗
  27. DeepSeek V4 Pro DeepSeek · Jul 2026
    69.5
    100 gates53 panel- human
    Open live ↗
  28. Qwen 3.7 Max Alibaba · Jul 2026
    69.3
    100 gates75 panel35 human
    Open live ↗
  29. GPT-5.6 Luna OpenAI · Jul 2026
    68.5
    100 gates70 panel40 human
    Open live ↗
  30. Claude Haiku 4.5 Anthropic · Jul 2026
    58.0
    100 gates50 panel35 human
    Open live ↗

Scores are the blended final: 25% browser gates, 45% blind three-lab panel, 30% blind human rating; unrated cells redistribute the human weight. Screenshots are the gate run at 1440×900. "Run it live" loads the untouched deliverable in a sandboxed frame - bugs included. Back to the leaderboard · Compare the top two