| text,label,label_name |
| What is 48 + 4?,10,Fast/simple |
| Localize this ad copy about the industrial revolution into Arabic.,6,Translation |
| "Search the web for wildlife conservation, then book a flight and send me a summary.",4,Agentic |
| Write a letter to my future self about the ocean floor.,5,Creative |
| Find and extract organizations and prices from this text.,8,Extraction |
| Is this statement a fact or an opinion: 'the immune system is largely misunderstood.'?,7,Classification |
| Interpret this legal clause into plain Dutch.,6,Translation |
| Draft a whimsical flash-fiction piece about the jazz era.,5,Creative |
| What is 33 + 10?,10,Fast/simple |
| What is 5 + 15?,10,Fast/simple |
| Debug this TypeError that occurs when running my script.,2,Coding |
| Process this 500-page thesis on blockchain; then explain the compliance requirements.,9,Long-context |
| "Given this 50-page transcript about renewable energy, list every deadline.",9,Long-context |
| Extract the main keyword phrases and topics from this passage on medieval castles.,8,Extraction |
| Give me the Swahili equivalent of this idiom: 'bite the bullet'.,6,Translation |
| Summarize this entire year of meeting notes covering climate change.,9,Long-context |
| What is the capital of Reykjavik?,0,QA |
| Give me a clear definition of the internet of things.,0,QA |
| Here is the full regulatory filing for ancient Greek philosophy (25-page). Extract the key clauses.,9,Long-context |
| "Call the API to get data on the human brain, then summarize the response and save it to disk.",4,Agentic |
| What is 14 + 21?,10,Fast/simple |
| What time is it in Cairo right now?,10,Fast/simple |
| Extract the main keyword phrases and topics from this passage on the solar system.,8,Extraction |
| "Orchestrate a multi-step workflow: fetch data, clean it, train a model, and return a report on the internet of things.",4,Agentic |
| Is this statement a fact or an opinion: 'space telescopes is largely misunderstood.'?,7,Classification |
| Which topic does this paragraph best belong to? oceanography mentions players.,7,Classification |
| Write a letter to my future self about modern architecture.,5,Creative |
| Extract the key entities from this invoice about artificial intelligence.,8,Extraction |
| Who is Isaac Newton known for?,0,QA |
| Determine whether this tweet about the stock market is positive or negative.,7,Classification |
| Use your registry of tools to send an email and report back in a short message.,4,Agentic |
| Who is Marie Curie known for?,0,QA |
| Translate the following business email into German.,6,Translation |
| "Call the API to get data on volcanoes, then summarize the response and save it to disk.",4,Agentic |
| Write a TypeScript script to batch-resize images.,2,Coding |
| How does a combustion engine actually work?,0,QA |
| What is 22 + 14?,10,Fast/simple |
| What is 17 + 9?,10,Fast/simple |
| Review this entire contract and extract the risks.,9,Long-context |
| Here is the full report for bees and pollination (25-page). Extract the key clauses.,9,Long-context |
| Write a letter to my future self about the immune system.,5,Creative |
| Review this long codebase README and tell me the setup steps.,9,Long-context |
| Summarize this entire year of meeting notes covering the immune system.,9,Long-context |
| What is the difference between electric vehicles and Mars exploration?,0,QA |
| "Classify the tone of this message as friendly, professional, or frustrated.",7,Classification |
| Write a function that restructure a nested JSON and returns a generator.,2,Coding |
| Create a dialogue between two characters arguing about modern architecture.,5,Creative |
| Pull the named entities and keywords out of this invoice about Renaissance art.,8,Extraction |
| Read these 15 documents about the internet of things and synthesize a single answer.,9,Long-context |
| Which topic does this paragraph best belong to? the industrial revolution mentions players.,7,Classification |
| What are the main causes of Mars exploration?,0,QA |
| What is 2 + 20?,10,Fast/simple |
| "Given this 300-page thesis about ancient Egypt, return a structured overview.",9,Long-context |
| Draft a melancholic flash-fiction piece about oceanography.,5,Creative |
| Analyze this full 200-page report on wildlife conservation and summarize the conclusions.,9,Long-context |
| Compose the opening lines of a mystery novel set in a space station.,5,Creative |
| Is this statement a fact or an opinion: 'deep-sea creatures is largely misunderstood.'?,7,Classification |
| Analyze this full 200-page report on ancient Greek philosophy and summarize the conclusions.,9,Long-context |
| Give me the Greek equivalent of this idiom: 'bite the bullet'.,6,Translation |
| Convert this English text to Mandarin and keep the tone neutral.,6,Translation |
| Translate 'Good morning' into Swahili.,6,Translation |
| Use your registry of tools to monitor a server and report back in a short message.,4,Agentic |
| Summarize the key findings from this research paper on space telescopes.,1,Summary |
| What is the difference between the ocean floor and bees and pollination?,0,QA |
| Condense this chapter into the main takeaways about the Silk Road.,1,Summary |
| "Provide a brief summary of the meeting notes, focusing on the ocean floor.",1,Summary |
| Condense this chapter into the main takeaways about coral reefs.,1,Summary |
| "If the probability of rain is 57%, what is the chance it does not rain?",3,Reasoning |
| What is the capital of Paris?,0,QA |
| Explain the immune system in simple terms.,0,QA |
| Write a letter to my future self about basketball.,5,Creative |
| What is 12 + 11?,10,Fast/simple |
| What is 19 + 15?,10,Fast/simple |
| Explain the time complexity of this algorithm that validate an email.,2,Coding |
| Extract the key entities from this meeting minutes about the ocean floor.,8,Extraction |
| Design a schema for an app that tracks the Kalahari desert.,2,Coding |
| Which topic does this paragraph best belong to? Renaissance art mentions algorithms.,7,Classification |
| Compose a haiku about traditional cuisine.,5,Creative |
| "Call the API to get data on modern architecture, then summarize the response and save it to disk.",4,Agentic |
| Localize this ad copy about the moon landing into Swahili.,6,Translation |
| "Coordinate a multi-agent system: one agent searches the ocean floor, another drafts a plan, and I review the result.",4,Agentic |
| What is 34 + 15?,10,Fast/simple |
| What is the difference between modern architecture and space telescopes?,0,QA |
| Translate these product instructions into Spanish.,6,Translation |
| "Coordinate a multi-agent system: one agent searches Renaissance art, another drafts a plan, and I review the result.",4,Agentic |
| "Extract named entities (people, places, organizations) from this text about culinary history.",8,Extraction |
| Which topic does this paragraph best belong to? Renaissance art mentions budgets.,7,Classification |
| Here is a 300-page report. Analyze it and summarize the key provisions.,9,Long-context |
| Convert this English text to Dutch and keep the tone casual.,6,Translation |
| "Extract named entities (people, places, organizations) from this text about the solar system.",8,Extraction |
| "Which of these topics is this text about: traditional cuisine, machine learning, oceanography?",7,Classification |
| "Tag this invoice with one of: urgent, normal, low priority.",7,Classification |
| Write a function that find duplicates and returns a generator.,2,Coding |
| Mary buys 3 apples at $1 each and a loaf for $2. Total cost?,3,Reasoning |
| Translate these product instructions into Arabic.,6,Translation |
| "Given this 50-page contract about traditional cuisine, identify contradictions.",9,Long-context |
| Write a SQL query to get the top 6 orders by revenue.,2,Coding |
| Extract all product names present in the following report.,8,Extraction |
| Determine whether this tweet about wildlife conservation is positive or negative.,7,Classification |
| "You are an agent with browsing, retrieval, and code execution skills. Achieve: the industrial revolution.",4,Agentic |
| Give me a clear definition of machine learning.,0,QA |
| Mary buys 2 apples at $3 each and a loaf for $3. Total cost?,3,Reasoning |
| Extract the main keyword phrases and topics from this passage on renewable energy.,8,Extraction |
| Explain this build script to me.,2,Coding |
| Write a function that compute the Fibonacci sequence and returns a list.,2,Coding |
| Condense this chapter into the main takeaways about the ocean floor.,1,Summary |
| "Which of these topics is this text about: electric vehicles, climate change, Mars exploration?",7,Classification |
| Extract all dates and person names from the text about machine learning.,8,Extraction |
| Give me the Greek equivalent of this idiom: 'spill the beans'.,6,Translation |
| Compose a haiku about ancient Greek philosophy.,5,Creative |
| "Which of these numbers is the odd one out and why: [75, 14, 78, 60]?",3,Reasoning |
| Pull out the tracking number from this receipt.,8,Extraction |
| Write unit tests for this caching layer.,2,Coding |
| Here is the full transcript for the Great Barrier Reef (120-page). List the action items.,9,Long-context |
| "Split this goal into a sequence of actions, each with a recommended tool, then execute them in order.",4,Agentic |
| Give me a clear definition of wildlife conservation.,0,QA |
| "If the probability of rain is 65%, what is the chance it does not rain?",3,Reasoning |
| Scan this contract and extract every dates.,8,Extraction |
| Draft a whimsical flash-fiction piece about the moon landing.,5,Creative |
| "If the probability of rain is 72%, what is the chance it does not rain?",3,Reasoning |
| "List every name, date, amount mentioned in this report on wildlife conservation.",8,Extraction |
| "You are an agent with browsing, retrieval, and code execution skills. Achieve: the ocean floor.",4,Agentic |
| Draft a whimsical flash-fiction piece about the ocean floor.,5,Creative |
| Explain the human brain in plain terms.,0,QA |
| Which topic does this paragraph best belong to? basketball mentions players.,7,Classification |
| When was the telephone invented?,0,QA |
| Give me the German equivalent of this idiom: 'break the ice'.,6,Translation |
| "If 11 books each have a unique title, how many distinct titles are there?",3,Reasoning |
| Determine whether this tweet about the moon landing is positive or negative.,7,Classification |
| Write a TypeScript script to monitor a log file.,2,Coding |
| Extract the main keyword phrases and topics from this passage on skyscrapers.,8,Extraction |
| Write a Rust script to back up a database.,2,Coding |
| Draft a melancholic flash-fiction piece about artificial intelligence.,5,Creative |
| How do you say volcanoes in French?,6,Translation |
| Write a one-paragraph summary of this report on the industrial revolution.,1,Summary |
| "If the probability of rain is 66%, what is the chance it does not rain?",3,Reasoning |
| Make a concise summary of the key points in this transcript about renewable energy.,1,Summary |
| Review this entire codebase README and identify contradictions.,9,Long-context |
| "Call the API to get data on the Roman Empire, then summarize the response and save it to disk.",4,Agentic |
| Summarize this article about the moon landing in three bullet points.,1,Summary |
| Explain artificial intelligence in plain terms.,0,QA |
| Use your registry of tools to send an email and report back in a JSON summary.,4,Agentic |
| "Which of these topics is this text about: Renaissance art, bees and pollination, ancient Greek philosophy?",7,Classification |
| A train departs at 8:00 traveling at 80 mph; how far in 4 hours?,3,Reasoning |
| Briefly summarize the plot of this story about wildlife conservation.,1,Summary |
| Extract all emails and phone numbers and ingredients from the text about renewable energy.,8,Extraction |
| What are the main causes of coral reefs?,0,QA |
| "Search the web for the stock market, then book a hotel and send me a summary.",4,Agentic |
| Translate 'How are you today' into French.,6,Translation |
| Find and extract legal terms and emails and phone numbers from this text.,8,Extraction |
| Summarize this article about the internet of things in one line.,1,Summary |
| Write a short executive summary of this report on Mars exploration.,1,Summary |
| Compose a haiku about electric vehicles.,5,Creative |
| Give me the Greek equivalent of this idiom: 'break the ice'.,6,Translation |
| Write a SQL query to get the top 2 orders by revenue.,2,Coding |
| What is 39 + 21?,10,Fast/simple |
| Localize this ad copy about the ocean floor into Dutch.,6,Translation |
| Render this quote into Russian and explain any nuances.,6,Translation |
| Pull the key stats and numbers out of this receipt about photography.,8,Extraction |
| What are the main causes of the Kalahari desert?,0,QA |
| A train departs at 12:00 traveling at 82 mph; how far in 5 hours?,3,Reasoning |
| "You are an agent with browsing, retrieval, and code execution skills. Achieve: Mars exploration.",4,Agentic |
| Convert this English text to Japanese and keep the tone neutral.,6,Translation |
| "There are 7 boxes, one holds a prize. If I open 8 wrong boxes, how many remain?",3,Reasoning |
| Summarize the key findings from this research paper on the French Revolution.,1,Summary |
| What is the difference between the French Revolution and the human genome?,0,QA |
| "Which of these topics is this text about: wildlife conservation, modern architecture, space telescopes?",7,Classification |
| "Use the file tool to open data.csv, then the search tool for quantum computing, then combine both.",4,Agentic |
| Give me a clear definition of quantum computing.,0,QA |
| Create a catchy tagline for a company that sells coffee.,5,Creative |
| Create a dialogue between two characters arguing about the human brain.,5,Creative |
| What's the weather like in Tokyo today?,10,Fast/simple |
| "Coordinate a multi-agent system: one agent searches the stock market, another drafts a plan, and I review the result.",4,Agentic |
| Draft a melancholic flash-fiction piece about the French Revolution.,5,Creative |
| Interpret this legal clause into plain Italian.,6,Translation |
| Mary buys 2 apples at $1 each and a loaf for $5. Total cost?,3,Reasoning |
| Give me a 3-bullet recap of the immune system.,1,Summary |
| Give me a TL;DR of the following passage about skyscrapers.,1,Summary |
| Draft a melancholic flash-fiction piece about the Roman Empire.,5,Creative |
| What is 15 + 2?,10,Fast/simple |
| Extract the main keyword phrases and topics from this passage on the moon landing.,8,Extraction |
| Debug this KeyError that occurs when running my script.,2,Coding |
| Process this 300-page user manual on Mars exploration; then extract the recommendations.,9,Long-context |
| Write a short story about a time-traveling librarian.,5,Creative |
| Review this entire legal document and identify contradictions.,9,Long-context |
| "Use the file tool to open data.csv, then the search tool for the ocean floor, then combine both.",4,Agentic |
| "There are 3 boxes, one holds a prize. If I open 8 wrong boxes, how many remain?",3,Reasoning |
| Design a schema for an app that tracks volcanoes.,2,Coding |
| Compose a haiku about oceanography.,5,Creative |
| What is 44 + 44?,10,Fast/simple |
| Write a Java function to merge two sorted arrays.,2,Coding |
| What is the difference between photography and climate change?,0,QA |
| Explain the time complexity of this algorithm that find duplicates.,2,Coding |
| What is 2 + 10?,10,Fast/simple |
| "There are 5 boxes, one holds a prize. If I open 2 wrong boxes, how many remain?",3,Reasoning |
| "Call the API to get data on the jazz era, then summarize the response and save it to disk.",4,Agentic |
| Give me a TL;DR of the following passage about bees and pollination.,1,Summary |
| Draft a melancholic flash-fiction piece about the Great Barrier Reef.,5,Creative |
| Make a concise summary of the key points in this transcript about skyscrapers.,1,Summary |
| Write a docstring and type hints for a JavaScript function that processes space telescopes.,2,Coding |
| "Chain these actions: look up the weather, find a restaurant, and add it to my calendar in Sao Paulo.",4,Agentic |
| What is 40 + 14?,10,Fast/simple |
| What does BTW mean?,10,Fast/simple |
| Draft a whimsical flash-fiction piece about modern architecture.,5,Creative |
| "Provide a brief summary of the meeting notes, focusing on wildlife conservation.",1,Summary |
| "Use the file tool to open notes.txt, then the search tool for medieval castles, then combine both.",4,Agentic |
| Which topic does this paragraph best belong to? quantum computing mentions budgets.,7,Classification |
| Who is Leonardo da Vinci known for?,0,QA |
| Briefly summarize the plot of this story about coral reefs.,1,Summary |
| Explain the human brain in technical terms.,0,QA |
| Give me a clear definition of space telescopes.,0,QA |
| Which topic does this paragraph best belong to? the moon landing mentions budgets.,7,Classification |
| Write a SQL query to get the top 6 products by revenue.,2,Coding |
| What does ASAP mean?,10,Fast/simple |
| Compose a haiku about the Roman Empire.,5,Creative |
| Return a JSON object with dates and locations parsed from this order confirmation.,8,Extraction |
| Briefly summarize the plot of this story about climate change.,1,Summary |
| Here is a 50-page report. Analyze it and give the setup steps.,9,Long-context |
| What is 3 + 20?,10,Fast/simple |
| "Classify this email as spam, promotion, or important: 'You have won a free cruise!'",7,Classification |
| What is 35 + 32?,10,Fast/simple |
| Here is the full codebase README for artificial intelligence (120-page). Extract the key clauses.,9,Long-context |
| "Extract named entities (people, places, organizations) from this text about the stock market.",8,Extraction |
| Determine whether this tweet about machine learning is positive or negative.,7,Classification |
| What is 13 + 49?,10,Fast/simple |
| What is 33 + 34?,10,Fast/simple |
| What is 41 + 35?,10,Fast/simple |
| "Which of these numbers is the odd one out and why: [73, 51, 21, 40]?",3,Reasoning |
| Use your registry of tools to monitor a server and report back in a CSV.,4,Agentic |
| Extract the main keyword phrases and topics from this passage on ancient Greek philosophy.,8,Extraction |
| "Which of these topics is this text about: electric vehicles, culinary history, modern architecture?",7,Classification |
| Give me a TL;DR of the following passage about culinary history.,1,Summary |
| "Call the API to get data on traditional cuisine, then summarize the response and save it to disk.",4,Agentic |
| What is the capital of Oslo?,0,QA |
| What is 30 + 14?,10,Fast/simple |
| "Call the API to get data on Renaissance art, then summarize the response and save it to disk.",4,Agentic |
| What is the difference between medieval castles and the Roman Empire?,0,QA |
| "There are 3 boxes, one holds a prize. If I open 2 wrong boxes, how many remain?",3,Reasoning |
| How do you say bees and pollination in Hindi?,6,Translation |
| Which topic does this paragraph best belong to? oceanography mentions flights.,7,Classification |
| Make a concise summary of the key points in this transcript about deep-sea creatures.,1,Summary |
| "Which of these numbers is the odd one out and why: [19, 45, 32, 70]?",3,Reasoning |
| "Which of these numbers is the odd one out and why: [10, 52, 77, 38]?",3,Reasoning |
| Draft a melancholic flash-fiction piece about the solar system.,5,Creative |
| Mary buys 5 apples at $2 each and a loaf for $3. Total cost?,3,Reasoning |
| Translate these product instructions into Dutch.,6,Translation |
| "There are 3 boxes, one holds a prize. If I open 5 wrong boxes, how many remain?",3,Reasoning |
| Extract the key figures timestamp from this receipt.,8,Extraction |
| Translate the following business email into Dutch.,6,Translation |
| What is 11 + 36?,10,Fast/simple |
| "Using this long report about basketball, extract the recommendations.",9,Long-context |
| A train departs at 2:00 traveling at 63 mph; how far in 6 hours?,3,Reasoning |
| "Use the file tool to open config.json, then the search tool for modern architecture, then combine both.",4,Agentic |
| Give me a clear definition of the solar system.,0,QA |
| Explain oceanography in technical terms.,0,QA |
| Localize this ad copy about culinary history into Japanese.,6,Translation |
| "Use the file tool to open data.csv, then the search tool for the Great Barrier Reef, then combine both.",4,Agentic |
| "If Alice is taller than Bob and Bob is taller than Carol, who is the shortest?",3,Reasoning |
| Refactor this SQL query to be more readable.,2,Coding |
| "Return a JSON object with name, date, amount parsed from this invoice.",8,Extraction |
| Explain the time complexity of this algorithm that download and cache a page.,2,Coding |
| Draft a melancholic flash-fiction piece about deep-sea creatures.,5,Creative |
| Write unit tests for this data loader.,2,Coding |
| Extract the steps and ingredients from this recipe for blockchain.,8,Extraction |
| Compose a haiku about the Great Barrier Reef.,5,Creative |
| Translate 'How are you today' into Korean.,6,Translation |
| Scan this report and extract every dates.,8,Extraction |
| "Extract named entities (people, places, organizations) from this text about the jazz era.",8,Extraction |
| Write a SQL query to get the top 1 customers by revenue.,2,Coding |
| Mary buys 4 apples at $2 each and a loaf for $3. Total cost?,3,Reasoning |
| Summarize this article about bees and pollination in one line.,1,Summary |
| Write a function that download and cache a page and returns a list.,2,Coding |
| Draft a funny flash-fiction piece about Mars exploration.,5,Creative |
| Give me a TL;DR of the following passage about the jazz era.,1,Summary |
| Write a Rust function to sort a list of dicts.,2,Coding |
| What is 5 + 17?,10,Fast/simple |
| "Which of these numbers is the odd one out and why: [34, 18, 50, 63]?",3,Reasoning |
| A train departs at 12:00 traveling at 68 mph; how far in 2 hours?,3,Reasoning |
| Read these 15 documents about the human genome and synthesize a single answer.,9,Long-context |
| "There are 8 boxes, one holds a prize. If I open 3 wrong boxes, how many remain?",3,Reasoning |
| Draft a melancholic flash-fiction piece about climate change.,5,Creative |
| Is this statement a fact or an opinion: 'ancient Greek philosophy is largely misunderstood.'?,7,Classification |
| Give me a TL;DR of the following passage about volcanoes.,1,Summary |
| "Provide a brief summary of the product review, focusing on renewable energy.",1,Summary |
| Create a dialogue between two characters arguing about the stock market.,5,Creative |
| Create a Makefile target for a Rust project.,2,Coding |
| "Which of these topics is this text about: electric vehicles, bees and pollination, the industrial revolution?",7,Classification |
| Read this 10-page research paper and compare the revisions.,9,Long-context |
| Give me a clear definition of bees and pollination.,0,QA |
| Extract all key figures and product names from the text about the Silk Road.,8,Extraction |
| What are the main causes of blockchain?,0,QA |
| Extract the key entities from this insurance policy about renewable energy.,8,Extraction |
| Use your registry of tools to deploy a model and report back in a short message.,4,Agentic |
| Improve the performance of my Python program that parse a CSV.,2,Coding |
| Review this entire transcript and return a structured overview.,9,Long-context |
| "Search the web for ancient Egypt, then book a dinner and send me a summary.",4,Agentic |
| Write a docstring and type hints for a Java function that processes bees and pollination.,2,Coding |
| Explain the industrial revolution in technical terms.,0,QA |
| Summarize the key findings from this research paper on quantum computing.,1,Summary |
| What is the difference between the Silk Road and blockchain?,0,QA |
| What is 40 + 38?,10,Fast/simple |
| Localize this ad copy about space telescopes into Greek.,6,Translation |
| Make a concise summary of the key points in this transcript about culinary history.,1,Summary |
| Which topic does this paragraph best belong to? blockchain mentions recipes.,7,Classification |
| How do you say volcanoes in German?,6,Translation |
| A train departs at 8:00 traveling at 64 mph; how far in 5 hours?,3,Reasoning |
| Explain the human genome in simple terms.,0,QA |
| Create a catchy tagline for a company that sells sustainable products.,5,Creative |
| Review this entire transcript and identify contradictions.,9,Long-context |
| A train departs at 8:00 traveling at 69 mph; how far in 5 hours?,3,Reasoning |
| "You have access to a search tool, a calculator, and a file system. Please aggregate these 5 sources.",4,Agentic |
| Which topic does this paragraph best belong to? machine learning mentions budgets.,7,Classification |
| Read the whole 300-page dataset README which covers the immune system and compare the revisions.,9,Long-context |
| Translate the following business email into Russian.,6,Translation |
| What's the weather like in Toronto today?,10,Fast/simple |
| Briefly summarize the plot of this story about the jazz era.,1,Summary |
| How do you say the stock market in Greek?,6,Translation |
| Write a function that validate an email and returns a list.,2,Coding |
| Which topic does this paragraph best belong to? space telescopes mentions recipes.,7,Classification |
| What is the difference between the solar system and the Roman Empire?,0,QA |
| "You have access to a search tool, a calculator, and a file system. Please compute this value.",4,Agentic |
| "If the probability of rain is 55%, what is the chance it does not rain?",3,Reasoning |
| What is 6 + 42?,10,Fast/simple |
| Write a Rust function to normalize a phone number.,2,Coding |
| Write a Go function to parse a CSV.,2,Coding |
| Compose a haiku about quantum computing.,5,Creative |
| What is the difference between artificial intelligence and photography?,0,QA |
| "Which of these topics is this text about: the Kalahari desert, deep-sea creatures, the stock market?",7,Classification |
| Optimize this nested loop to run faster.,2,Coding |
| "Search the web for the Kalahari desert, then book a flight and send me a summary.",4,Agentic |
| "Label the sentiment of this review as positive, negative, or neutral.",7,Classification |
| Give me a TL;DR of the following passage about deep-sea creatures.,1,Summary |
| "Which of these topics is this text about: basketball, the internet of things, wildlife conservation?",7,Classification |
| Extract all legal terms present in the following receipt.,8,Extraction |
| Mary buys 2 apples at $1 each and a loaf for $2. Total cost?,3,Reasoning |
| Create a dialogue between two characters arguing about blockchain.,5,Creative |
| "Orchestrate a multi-step workflow: fetch data, clean it, train a model, and return a report on Renaissance art.",4,Agentic |
| Create a dialogue between two characters arguing about the French Revolution.,5,Creative |
| Plan how an autonomous agent would complete the goal 'book a table for 4 near Tokyo'.,4,Agentic |
| "Use the file tool to open data.csv, then the search tool for electric vehicles, then combine both.",4,Agentic |
| "Use the file tool to open data.csv, then the search tool for ancient Greek philosophy, then combine both.",4,Agentic |
| A train departs at 4:00 traveling at 49 mph; how far in 6 hours?,3,Reasoning |
| What is 38 + 35?,10,Fast/simple |
| Analyze this full 200-page report on modern architecture and summarize the conclusions.,9,Long-context |
| Explain the immune system in beginner-friendly terms.,0,QA |
| Write a docstring and type hints for a JavaScript function that processes the Roman Empire.,2,Coding |
| "Which of these topics is this text about: the Roman Empire, climate change, the French Revolution?",7,Classification |
| Extract all person names present in the following product review.,8,Extraction |
| Read this 10-page regulatory filing and extract the recommendations.,9,Long-context |
| Compose a haiku about Mars exploration.,5,Creative |
| Write a SQL query to get the top 9 products by revenue.,2,Coding |
| Process this multi-page PDF and give a structured overview.,9,Long-context |
| Draft a funny flash-fiction piece about electric vehicles.,5,Creative |
| "Coordinate a multi-agent system: one agent searches the immune system, another drafts a plan, and I review the result.",4,Agentic |
| Create a Makefile target for a Python project.,2,Coding |
| Summarize this 10-page document in under 80 words.,1,Summary |
| What is 26 + 28?,10,Fast/simple |
| Here is the full legal document for bees and pollination (10-page). Extract the key clauses.,9,Long-context |
| "Search the web for machine learning, then book a hotel and send me a summary.",4,Agentic |
| Summarize this article about culinary history in two sentences.,1,Summary |
| Scan this report and extract every prices.,8,Extraction |
| What is 33 + 47?,10,Fast/simple |
| What is the capital of Sydney?,0,QA |
| "Use the file tool to open config.json, then the search tool for machine learning, then combine both.",4,Agentic |
| Pull out the due date from this contract.,8,Extraction |
| What is 3 + 17?,10,Fast/simple |
| Render this quote into Japanese and explain any nuances.,6,Translation |
| "Sort these customer complaints into billing, technical, or service.",7,Classification |
| Write a SQL query to get the top 8 products by revenue.,2,Coding |
| Here is a 10-page user manual. Analyze it and identify contradictions.,9,Long-context |
| "Call the API to get data on the Kalahari desert, then summarize the response and save it to disk.",4,Agentic |
| "You are an agent with browsing, retrieval, and code execution skills. Achieve: ancient Greek philosophy.",4,Agentic |
| Draft a funny flash-fiction piece about renewable energy.,5,Creative |
| Draft a whimsical flash-fiction piece about ancient Egypt.,5,Creative |
| Find the memory leak in this Go worker.,2,Coding |
| Extract the patient's symptoms and prescribed medication from this note.,8,Extraction |
| Which topic does this paragraph best belong to? quantum computing mentions flights.,7,Classification |
| "Extract named entities (people, places, organizations) from this text about the moon landing.",8,Extraction |
| "If 6 books each have a unique title, how many distinct titles are there?",3,Reasoning |
| Briefly summarize the plot of this story about artificial intelligence.,1,Summary |
| Which topic does this paragraph best belong to? medieval castles mentions budgets.,7,Classification |
| What is 29 + 27?,10,Fast/simple |
| Translate the following business email into French.,6,Translation |
| "Read this 1,000-line thesis and give the setup steps.",9,Long-context |
| What is the difference between traditional cuisine and the stock market?,0,QA |
| Find and extract legal terms and geographic locations from this text.,8,Extraction |
| What is 44 + 46?,10,Fast/simple |
| How do you say the French Revolution in Greek?,6,Translation |
| Write a SQL query to get the top 5 customers by revenue.,2,Coding |
| Which topic does this paragraph best belong to? the human brain mentions recipes.,7,Classification |
| Explain medieval castles in simple terms.,0,QA |
| "Which of these topics is this text about: skyscrapers, electric vehicles, bees and pollination?",7,Classification |
| "Which of these numbers is the odd one out and why: [65, 4, 77, 69]?",3,Reasoning |
| "Classify this email as spam, promotion, or important: 'You have won a free vacation!'",7,Classification |
| Which topic does this paragraph best belong to? electric vehicles mentions players.,7,Classification |
| Give me a one-sentence recap of ancient Egypt.,1,Summary |
| "Search the web for skyscrapers, then book a hotel and send me a summary.",4,Agentic |
| Translate these product instructions into Swahili.,6,Translation |
| Convert this English text to Greek and keep the tone formal.,6,Translation |
| Translate 'Thank you very much' into Swahili.,6,Translation |
| Condense this chapter into the main takeaways about blockchain.,1,Summary |
| Extract all prices present in the following product review.,8,Extraction |
| Draft a melancholic flash-fiction piece about quantum computing.,5,Creative |
| Summarize this article about volcanoes in three bullet points.,1,Summary |
| Summarize this article about oceanography in one line.,1,Summary |
| Convert this pseudocode into working Rust code.,2,Coding |
| A train departs at 8:00 traveling at 61 mph; how far in 4 hours?,3,Reasoning |
| Write a product description for a noise-cancelling earbuds.,5,Creative |
| What is 34 + 29?,10,Fast/simple |
| Explain the ocean floor in technical terms.,0,QA |
| Mary buys 4 apples at $1 each and a loaf for $3. Total cost?,3,Reasoning |
| "Search the web for the Kalahari desert, then book a dinner and send me a summary.",4,Agentic |
| "Which of these numbers is the odd one out and why: [4, 1, 23, 75]?",3,Reasoning |
| What is the difference between the solar system and climate change?,0,QA |
| Extract the key entities from this contract about photography.,8,Extraction |
| Give me a clear definition of modern architecture.,0,QA |
| Interpret this legal clause into plain French.,6,Translation |
| Which topic does this paragraph best belong to? medieval castles mentions players.,7,Classification |
| What is 14 + 26?,10,Fast/simple |
| "Here is a 1,000-line codebase README. Analyze it and return a structured overview.",9,Long-context |
| Read the whole 50-page regulatory filing which covers ancient Greek philosophy and summarize the key provisions.,9,Long-context |
| "Using this long regulatory filing about deep-sea creatures, compare the revisions.",9,Long-context |
| What is 39 + 5?,10,Fast/simple |
| What is 15 + 42?,10,Fast/simple |
| Refactor this function to be more readable.,2,Coding |
| Build a a CSV importer with proper error handling.,2,Coding |
| Localize this ad copy about the moon landing into Russian.,6,Translation |
| Find and extract key figures and prices from this text.,8,Extraction |
| Here is the full thesis for quantum computing (25-page). Extract the key clauses.,9,Long-context |
| Summarize this entire year of meeting notes covering the internet of things.,9,Long-context |
| Improve the performance of my Python program that tokenize a sentence.,2,Coding |
| Is this statement a fact or an opinion: 'Renaissance art is largely misunderstood.'?,7,Classification |
| Compose a haiku about the immune system.,5,Creative |
| Review this entire legal document and answer the question about cost.,9,Long-context |
| "Call the API to get data on artificial intelligence, then summarize the response and save it to disk.",4,Agentic |
| Give me an executive recap of the stock market.,1,Summary |
| Translate 'I would like a coffee' into Italian.,6,Translation |
| Scan this contract and extract every organizations.,8,Extraction |
| Is this statement a fact or an opinion: 'the Roman Empire is largely misunderstood.'?,7,Classification |
| A train departs at 1:00 traveling at 49 mph; how far in 6 hours?,3,Reasoning |
| "There are 9 boxes, one holds a prize. If I open 5 wrong boxes, how many remain?",3,Reasoning |
| A train departs at 12:00 traveling at 45 mph; how far in 4 hours?,3,Reasoning |
| Create a catchy tagline for a company that sells handmade furniture.,5,Creative |
| How do you say medieval castles in Dutch?,6,Translation |
| "Given this 10-page regulatory filing about skyscrapers, extract the recommendations.",9,Long-context |
| Optimize this pandas operation to run faster.,2,Coding |
| Write a one-paragraph summary of this report on climate change.,1,Summary |
| Write a letter to my future self about volcanoes.,5,Creative |
| Give me a 3-bullet recap of electric vehicles.,1,Summary |
| Read this 500-page legal document and extract the risks.,9,Long-context |
| A train departs at 12:00 traveling at 64 mph; how far in 6 hours?,3,Reasoning |
| "Extract named entities (people, places, organizations) from this text about renewable energy.",8,Extraction |
| What is 18 + 2?,10,Fast/simple |
| "Which of these numbers is the odd one out and why: [9, 49, 30, 26]?",3,Reasoning |
| Mary buys 5 apples at $1 each and a loaf for $4. Total cost?,3,Reasoning |
| Localize this ad copy about coral reefs into Spanish.,6,Translation |
| What are the main causes of machine learning?,0,QA |
| "Provide a brief summary of the product review, focusing on the French Revolution.",1,Summary |
| Translate these product instructions into Russian.,6,Translation |
| "List every people, places, organizations mentioned in this invoice on Renaissance art.",8,Extraction |
| What is 40 + 40?,10,Fast/simple |
| Translate this paragraph into Hindi: 'The quick brown fox jumps over the lazy dog.',6,Translation |
| What is the difference between bees and pollination and volcanoes?,0,QA |
| "Given this lengthy source, extract the section that discusses compliance.",9,Long-context |
| Design a schema for an app that tracks deep-sea creatures.,2,Coding |
| Extract the main keyword phrases and topics from this passage on the Great Barrier Reef.,8,Extraction |
| Translate these product instructions into Greek.,6,Translation |
| Create a dialogue between two characters arguing about the Silk Road.,5,Creative |
| "Pull the name, date, amount out of this news article about the ocean floor.",8,Extraction |
| Process this 120-page user manual on bees and pollination; then return a structured overview.,9,Long-context |
| Condense this chapter into the main takeaways about the jazz era.,1,Summary |
| Here is a 120-page transcript. Analyze it and identify contradictions.,9,Long-context |
| "There are 5 boxes, one holds a prize. If I open 1 wrong boxes, how many remain?",3,Reasoning |
| "Tag this post with one of: urgent, normal, low priority.",7,Classification |
| Summarize the key findings from this research paper on modern architecture.,1,Summary |
| Which topic does this paragraph best belong to? blockchain mentions budgets.,7,Classification |
| Convert this English text to French and keep the tone neutral.,6,Translation |
| What is 14 + 12?,10,Fast/simple |
| "If 9 books each have a unique title, how many distinct titles are there?",3,Reasoning |
| Make a concise summary of the key points in this transcript about traditional cuisine.,1,Summary |
| Give me a 3-bullet recap of modern architecture.,1,Summary |
| What is 38 + 37?,10,Fast/simple |
| Process this 500-page contract on the Kalahari desert; then summarize the main conclusions.,9,Long-context |
| Draft a funny flash-fiction piece about space telescopes.,5,Creative |
| |
