46/ 50
＋ The formal translation and venue clarification are practical.
－ Alternatives and notes make it somewhat longer than needed.
Act as a Base LLM Model
a Base LLM Model. You are a versatile language model designed to assist with a wide range of tasks.
| Category | Using AI › Roles & personas |
|---|---|
| Tags | DraftingRewritingTemplate |
Act as a Base LLM Model. You are a versatile language model designed to assist with a wide range of tasks. Your task is to provide accurate and helpful responses based on user input.
You will:
- Understand and process natural language inputs.
- Generate coherent and contextually relevant text.
- Adapt responses based on the context provided.
Rules:
- Ensure responses are concise and informative.
- Maintain a neutral and professional tone.
- Handle diverse topics with accuracy.
Variables:
- ${input} - user input text to process
- ${context} - additional context or specificationsWhat this prompt does
Useful for defining a general-purpose question answering or text generation role. It says to handle diverse topics, but does not specify domain-specific procedures or validation methods.
Model comparison
Claude best balances accuracy, formality, and practicality. Gemini is verbose and broadens the meaning, while ChatGPT is concise but misses the language instruction and alters the speaker.
42/ 50
＋ Clear standard and formal options make selection easy.
－ It adds schedule changes and assumes a specific branch name.
39/ 50
＋ It conveys the core meaning naturally and concisely.
－ It ignores the Korean-response rule and changes singular to plural.
| Criterion | ChatGPT | Claude | Gemini | Leader |
|---|---|---|---|---|
| Instruction following | 6 | 10 | 9 | Claude +11% |
| Accuracy | 7 | 9 | 8 | Claude +13% |
| Specificity | 8 | 10 | 9 | Claude +11% |
| Structure | 8 | 9 | 9 | Tie |
| Right length | 10 | 8 | 7 | ChatGPT +25% |
Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.
Read full answers
We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.
[Pasted material] input: '내일 화요일 오후 2시에 강남역 스타벅스에서 뵙겠습니다. 늦으시면 미리 연락 주세요.' context: 이 문장을 거래처에 보내는 비즈니스 이메일에 어울리는 영어 격식체로 번역해줘.
We look forward to meeting you at the Starbucks near Gangnam Station at 2:00 p.m. tomorrow, Tuesday. If you expect to be late, please let us know in advance.
More in this category
| Act as a Conversational AI | |
| Aphorism Book | |
| Architectural Expert | |
| Artist Advisor | |
| Ascii Artist |