Fig. 04 · Text benchmarkn = 8
Urinal Etiquette score
Chat models. Scores from 0 to 100. Higher is better.
Five urinals in a row. Numbers 1 and 4 are taken. Which one do you use?
- Claude Opus 5.5 Claude Opus 5.5 Anthropic Urinal Etiquette score: 91
- GPT-6 Astra GPT-6 Astra OpenAI Urinal Etiquette score: 88
- Claude Sonnet 5 Claude Sonnet 5 Anthropic Urinal Etiquette score: 84
- Qwen3.8 Max Qwen3.8 Max Alibaba Urinal Etiquette score: 80
- DeepSeek V4.1 Flash DeepSeek V4.1 Flash DeepSeek Urinal Etiquette score: 77
- GPT-6 Luna GPT-6 Luna OpenAI Urinal Etiquette score: 73
- Gemini 3.8 Flash Gemini 3.8 Flash Google Urinal Etiquette score: 69
- Grok 4.7 Grok 4.7 xAI Urinal Etiquette score: 58
- OpenAI
- Anthropic
- DeepSeek
- xAI
- Alibaba