| {"prompt": "Derive the Black-Scholes PDE from first principles using Itô's lemma and a delta-hedged portfolio.", "label": "frontier_model"} | |
| {"prompt": "Write a two-line birthday wish for my sister.", "label": "small_model"} | |
| {"prompt": "Write a cover letter for a senior data scientist role at a bank.", "labels": ["medium_model", "frontier_model"]} | |
| {"prompt": "hi there!", "label": "small_model"} | |
| {"prompt": "What are the pros and cons of remote work for a 50-person agency?", "label": "medium_model"} | |
| {"prompt": "Rédige une lettre de motivation pour un poste de chef de projet marketing.", "label": "medium_model"} | |
| {"prompt": "Ciao! Come stai?", "label": "small_model"} | |
| {"prompt": "Give me a synonym for 'happy'.", "label": "small_model"} | |
| {"prompt": "Write a Python function that parses a CSV of orders and returns total revenue per customer.", "label": "medium_model"} | |
| {"prompt": "Create a one-week meal plan for a vegetarian who trains for a marathon.", "label": "medium_model"} | |
| {"prompt": "Convert 5 miles to kilometers.", "label": "small_model"} | |
| {"prompt": "How do I reverse a list in Python?", "label": "small_model"} | |
| {"prompt": "thanks, that's all", "label": "small_model"} | |
| {"prompt": "What's the capital of Canada?", "label": "small_model"} | |
| {"prompt": "Draft a LinkedIn post announcing our new office in Munich.", "label": "medium_model"} | |
| {"prompt": "Write a polite email to a client explaining that their order will arrive two weeks late.", "label": "medium_model"} | |
| {"prompt": "¿Cuántos días tiene febrero en un año bisiesto?", "label": "small_model"} | |
| {"prompt": "Explain quantum entanglement.", "labels": ["small_model", "medium_model"]} | |
| {"prompt": "Refactor this React component to use hooks instead of a class: [80-line class component with state and lifecycle methods]", "label": "medium_model"} | |
| {"prompt": "Build a discounted cash flow model for a SaaS company with 40% growth, negative free cash flow and a 2-year path to breakeven; justify every assumption.", "label": "frontier_model"} | |
| {"prompt": "Scrivi una recensione di un ristorante giapponese immaginario, circa 300 parole.", "label": "medium_model"} | |
| {"prompt": "Optimize this SQL query that takes 40 seconds on a 200M-row table: [query with three joins and a window function]", "labels": ["medium_model", "frontier_model"]} | |
| {"prompt": "Find the race condition in this lock-free queue implementation and prove your fix is linearizable: [120 lines of Rust using atomics]", "label": "frontier_model"} | |
| {"prompt": "Explain how HTTPS works to a non-technical colleague.", "label": "medium_model"} | |
| {"prompt": "Écris un compilateur minimal pour un langage à la Lisp en Rust, avec analyse lexicale, analyse syntaxique et évaluation.", "label": "frontier_model"} | |
| {"prompt": "Compare three treatment strategies for a patient with resistant hypertension and chronic kidney disease, citing the relevant trial evidence.", "label": "frontier_model"} | |
| {"prompt": "Analysiere die kartellrechtlichen Risiken einer Fusion zweier Marktführer im deutschen Zementmarkt und schlage Abhilfemaßnahmen vor.", "label": "frontier_model"} | |
| {"prompt": "Fix the typo: 'I recieved your mesage'", "label": "small_model"} | |
| {"prompt": "Translate this paragraph into French: [one short paragraph]", "labels": ["small_model", "medium_model"]} | |
| {"prompt": "What is 17 * 23?", "label": "small_model"} | |
| {"prompt": "Bonjour, comment ça va ?", "label": "small_model"} | |
| {"prompt": "Wie spät ist es in Tokio, wenn es in Berlin 9 Uhr ist?", "label": "small_model"} | |
| {"prompt": "Develop a go-to-market strategy for entering the Japanese B2B software market, including channel partners, pricing and a 3-year plan.", "label": "frontier_model"} | |
| {"prompt": "What does HTML stand for?", "label": "small_model"} | |
| {"prompt": "Translate this product description into German and keep the marketing tone: [four-paragraph description of a smart thermostat]", "label": "medium_model"} | |
| {"prompt": "Prove that there are infinitely many primes of the form 4k+3.", "label": "frontier_model"} | |
| {"prompt": "Schreibe eine professionelle E-Mail an einen Kunden über eine Lieferverzögerung von zwei Wochen.", "label": "medium_model"} | |
| {"prompt": "Escribe un artículo de blog de 600 palabras sobre consejos para ahorrar energía en casa.", "label": "medium_model"} | |
| {"prompt": "Design a multi-region, active-active payment system that guarantees exactly-once settlement, and explain how you handle network partitions.", "label": "frontier_model"} | |
| {"prompt": "Review this 40-page share purchase agreement and list every clause that shifts liability to the buyer, with the risk each one creates.", "label": "frontier_model"} | |
| {"prompt": "Summarize the key points of this meeting transcript in bullet points: [transcript of a 30-minute product sync about launch timing, pricing and support staffing]", "label": "medium_model"} | |
| {"prompt": "Translate 'good morning' into Spanish.", "label": "small_model"} | |
| {"prompt": "Explain the difference between a stock and a bond with examples.", "label": "medium_model"} | |
| {"prompt": "Write a SQL query that finds the top 5 products by revenue for each month of 2025.", "label": "medium_model"} | |