| {"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 review for a fictional restaurant that had great food but terrible service."}, {"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": "Complete the sentence: An apple a day keeps the _____ away."}, {"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": "What is the square root of 64?"}, {"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": "What color is a ripe banana?"}, {"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": "What is 9 squared?"}, {"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": "What is the opposite of 'hot'?"}, {"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": "Translate this complex medical research abstract from English to Japanese, maintaining specialized terminology."}, {"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": "Create a custom memory allocator module in Python simulating malloc and free using byte arrays."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"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 first letter of the alphabet?"}, {"role": "assistant", "content": "{\"model_tier\": 1, \"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": "Create a Python script to perform binary search on a sorted rotated array to find a target element."}, {"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": "Write a dialogue between two friends arguing about what movie to watch."}, {"role": "assistant", "content": "{\"model_tier\": 2, \"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 5 + 7?"}, {"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": "Write an algorithm that uses a Trie data structure to implement an autocomplete system."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"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": "If a printing press can print 500 pages in 4 hours, how many pages can it print in 7 hours?"}, {"role": "assistant", "content": "{\"model_tier\": 2, \"confidence\": 0.99}"}]} | |
| {"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 function to count the frequency of words in a given string and return a dictionary."}, {"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": "Create a python implementation of a Bloom Filter with customizable hashing functions."}, {"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 a function that converts a Roman numeral to an integer."}, {"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": "Write a comprehensive risk assessment report for migrating a legacy monolithic application to AWS cloud infrastructure."}, {"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": "Create an algorithm to solve Sudoku puzzles using backtracking."}, {"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": "Which is a vehicle: Car or Apple?"}, {"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": "Solve for x: 3x + 5 = 20"}, {"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": "Explain the concept of supply and demand."}, {"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": "Create a function that computes the factorial of a number using iteration."}, {"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 function that implements Dijkstra's algorithm to find the shortest path in a weighted graph."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"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": "Create an algorithm to solve the N-Queens problem and return all distinct board configurations."}, {"role": "assistant", "content": "{\"model_tier\": 4, \"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": "Create a regular expression that matches valid IPv4 addresses, and explain each part of the regex."}, {"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": "Write a script that parses an abstract syntax tree (AST) for simple Python expressions and evaluates them safely."}, {"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": "Solve for x in the complex plane: x^4 = 1. Provide all roots."}, {"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": "Find the shortest distance between the parallel lines 3x - 4y + 5 = 0 and 3x - 4y - 10 = 0."}, {"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": "Write an algorithm to find the longest palindromic substring in a given string."}, {"role": "assistant", "content": "{\"model_tier\": 3, \"confidence\": 0.99}"}]} | |