| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Design a recommendation engine that combines collaborative filtering, content-based filtering, and knowledge graphs. Provide the full system architecture."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.88}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What is the time complexity of binary search?"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a research proposal for using reinforcement learning to optimize energy consumption in data centers."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.85}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Design an algorithm to solve the traveling salesman problem for up to 20 cities using dynamic programming with bitmask, and analyze its complexity."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Goodbye, have a nice day!"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Give me a recipe for scrambled eggs."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.87}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What is the difference between HTTP and HTTPS?"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.98}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Given a dataset of customer purchases, describe how you would build a recommendation system."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Hello, how are you?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.91}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "If a train travels 60 mph for 2.5 hours, how far does it go?"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain what photosynthesis is in simple terms."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.88}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain the proof of the Fundamental Theorem of Calculus and its connection to Riemann integration."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write an async Python function that fetches data from 3 APIs concurrently."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What year did World War II end?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.97}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain the difference between a list and a tuple in Python."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What does 'RSVP' stand for?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain backpropagation in neural networks step by step with a simple example."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.9}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Design a scalable real-time chat system that handles 10 million concurrent users. Include architecture diagram description, technology choices, and failure handling."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Who wrote Romeo and Juliet?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.88}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a Python function that reverses a string."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a technical blog post introduction about microservices vs monolithic architecture."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.95}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "How does garbage collection work in Java vs Python? Compare approaches."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.98}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain how a hash map works internally, including collision resolution strategies."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a comprehensive literature review on transformer architectures in NLP, covering attention mechanisms, positional encoding variants, and recent efficiency improvements."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Perform a security threat model for a healthcare application handling PHI data under HIPAA, including attack vectors, mitigations, and compliance checklist."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.95}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Analyze the trade-offs between SQL and NoSQL databases for an e-commerce platform."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Given a legacy monolithic e-commerce application, create a detailed migration plan to microservices including service boundaries, data migration strategy, and rollback plan."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What is the square root of 4?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "A farmer has 100 meters of fencing. What dimensions maximize the enclosed rectangular area? Show your work."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Debug this Python code that's supposed to find duplicates in a list but returns wrong results:\ndef find_dupes(lst):\n seen = []\n for i in lst:\n if i in lst:\n seen.append(i)\n return seen"}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Design the database schema for a social media application with posts, comments, and likes."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.94}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain the CAP theorem and its implications for distributed systems."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.91}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a 2000-word essay analyzing the ethical implications of artificial general intelligence, covering alignment, economic displacement, and governance."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Summarize the plot of The Great Gatsby in 3 sentences."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.95}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Explain the mathematical foundations of public-key cryptography, including RSA and elliptic curve cryptography, with proofs of correctness."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "How do you spell 'necessary'?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.92}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "How many days are in a week?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.94}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a haiku about autumn."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "List the top 5 most populated countries."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a Python function to find the longest common subsequence of two strings."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Analyze the complexity classes P, NP, and NP-Complete. Explain the P vs NP problem and discuss the implications of its resolution."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.87}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Convert this JSON to a Python dictionary: {\"name\": \"Alice\", \"age\": 30}"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Rewrite this sentence in passive voice: 'The cat chased the mouse.'"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Convert 100 Fahrenheit to Celsius"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.91}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Design a distributed consensus protocol that improves on Raft for geo-replicated databases. Describe the algorithm, prove its safety properties, and analyze liveness."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.96}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Implement a binary search tree with insert, delete, and search operations in Python."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Prove that the square root of 2 is irrational."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Write a comprehensive technical specification for a programming language with dependent types, including syntax, type-checking rules, and example programs."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.88}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What are the SOLID principles in software engineering? Explain each with an example."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.91}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What are three healthy breakfast options?"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.88}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Create a full curriculum for teaching machine learning to software engineers, including 12 weekly modules with learning objectives, readings, and projects."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"confidence\": 0.87}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What is the capital of France?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.97}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What is the boiling point of water?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.97}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Name the largest planet in our solar system."}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.94}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Translate 'The quick brown fox jumps over the lazy dog' to French."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.87}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What is 2 + 2?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.86}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Is water wet?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"confidence\": 0.89}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "Compare and contrast REST APIs vs GraphQL. When would you choose each?"}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.93}"}]} | |
| {"messages": [{"role": "system", "content": "You are a query complexity router for Mistral AI models. Given a user query, classify it into the appropriate model tier and provide a confidence score.\n\nOutput ONLY valid JSON in this exact format:\n{\"model_tier\": <1|2|3|4>, \"confidence\": <0.0-1.0>}\n\nTier definitions:\n- Tier 1 (small): Simple factual lookups, greetings, trivial math, yes/no questions\n- Tier 2 (medium): Summarization, translation, moderate reasoning, simple coding\n- Tier 3 (large): Complex analysis, multi-step reasoning, debugging, comparisons\n- Tier 4 (xlarge): Expert-level research, novel problem-solving, proofs, system design"}, {"role": "user", "content": "What are the pros and cons of remote work?"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.96}"}]} | |