Have we made a unicorn? Continuous SVG-pelican style benchmark

A human judge has been testing AI models daily by asking them to draw a unicorn in pure SVG, and no model has succeeded in 10 days. The benchmark will continue until a machine produces a drawing indistinguishable from a human's.

Have we made a unicorn? NO No for 10 days and counting. Every day, the latest AI models are asked to draw a unicorn in pure SVG. A human judges the results. The verdict, so far, is no — and it will stay that way until a machine draws one you can’t tell from a human’s. Today’s attempts - Anthropic Claude Haiku Latest - Anthropic Claude Sonnet Latest - Claude Opus 4.6 Fast - Claude Opus 4.7 - Claude Opus 4.7 Fast - Claude Opus 4.8 - Claude Opus 4.8 Fast - Claude Opus Latest - DeepSeek V4 Flash - DeepSeek V4 Pro - DeepSeek V4 Pro - DeepSeek V4 Pro - DeepSeek V4 Pro - GLM 5.1 - GPT Chat Latest - GPT-5.5 - GPT-5.5 Pro - Gemini 3.1 Flash Lite - Gemini 3.5 Flash - Gemini 3.5 Flash - Gemini 3.5 Flash - Gemma 4 26B A4B - Gemma 4 31B free - Google Gemini Flash Latest - Google Gemini Pro Latest - Granite 4.1 8B - Grok 4.3 - Grok Build 0.1 - Grok Build 0.1 - Grok Build 0.1 - Hy3 preview - Kimi K2.6 - Kimi K2.7 Code - LFM2.5-1.2B-Instruct free - Laguna M.1 free - Laguna XS.2 free - Ling-2.6-1T - Ling-2.6-flash - Llama 4 Maverick - MiMo-V2.5 - MiniMax M3 - Mistral Medium 3.5 - Mistral Medium 3.5 - Mistral Medium 3.5 - Mistral Medium 3.5 - MoonshotAI Kimi Latest - Nemotron 3 Nano 30B A3B free - Nemotron 3 Super free - Nemotron 3 Ultra - Nemotron 3 Ultra free - Nemotron Nano 12B 2 VL free - Nemotron Nano 9B V2 free - Nex-N2-Pro free - OpenAI GPT Latest - OpenAI GPT Mini Latest - Perceptron Mk1 - Qwen3 Next 80B A3B Instruct free - Qwen3.5 Plus 2026-04-20 - Qwen3.6 27B - Qwen3.6 35B A3B - Qwen3.6 Flash - Qwen3.6 Max Preview - Qwen3.7 Max - Qwen3.7 Plus - Qwen3.7 Plus - Qwen3.7 Plus - Qwen3.7 Plus - Ring-2.6-1T - Step 3.7 Flash - gpt-oss-120b free - gpt-oss-20b free