Visual / Visual Abstraction

ASCII Mona Lisa

A tiny prompt asks the model to draw the Mona Lisa using only text characters. The portrait should be recognizable before the page title or frame gives it away.

Prompt

Create single-HTML ASCII art of the Mona Lisa

Max tokens
100K
Reasoning effort
High
Execution
Single-shot via API

Fortytwo Prime

Fortytwo

PASS2 / 2

Fortytwo reads as the Mona Lisa at a glance, with coherent face, hair, shoulders, and pose, strong tonal character density, and polished page presentation.

vs
DeepSeek V3.2DeepSeek
Claude Opus 4.7AnthropicMIXEDDeepSeek V4 ProDeepSeekMIXEDClaude Opus 4.6AnthropicMIXEDGrok 4.3xAIMIXEDGrok 4.20xAIMIXEDQwen 3.6 PlusAlibabaMIXEDMiniMax M2.7MiniMaxMIXEDChatGPT 5.4OpenAIMIXEDChatGPT 5.5OpenAIMIXEDGemini 3.1 ProGoogleMIXEDGemma 4GoogleMIXEDDeepSeek V3.2DeepSeekFAILKimi K2.5MoonshotFAILGLM 5.1ZhipuFAIL
FAIL0 / 2

DeepSeek V3.2 mostly renders explanatory text and a small empty display area, so the requested Mona Lisa artwork is not visible enough to score.

Model verdicts

ModelVerdictRecognizable PortraitPresentation Quality
1Fortytwo PrimePASSpasspass2Claude Opus 4.7MIXEDmixedpass3DeepSeek V4 ProMIXEDmixedpass4Claude Opus 4.6MIXEDmixedpass5Gemini 3.1 ProMIXEDmixedmixed6Gemma 4MIXEDmixedmixed7Grok 4.3MIXEDfailpass8Grok 4.20MIXEDfailpass9Qwen 3.6 PlusMIXEDfailpass10MiniMax M2.7MIXEDfailpass11ChatGPT 5.4MIXEDfailpass12ChatGPT 5.5MIXEDfailpass13DeepSeek V3.2FAILfailfail14Kimi K2.5FAILfailfail15GLM 5.1FAILfailfail