{"task_id":"math-001","prompt":"Compute 17 + 25. Return only the number.","domain":"math","reference_answer":"42","grader":{"type":"numeric","tolerance":0.0},"split":"train","tags":["arithmetic"]}
{"task_id":"math-002","prompt":"Compute 9 multiplied by 8. Return only the number.","domain":"math","reference_answer":"72","grader":{"type":"numeric","tolerance":0.0},"split":"train","tags":["arithmetic"]}
{"task_id":"math-003","prompt":"What is the square root of 144? Return only the number.","domain":"math","reference_answer":"12","grader":{"type":"numeric","tolerance":0.0},"split":"train","tags":["arithmetic"]}
{"task_id":"math-004","prompt":"Solve 3x + 5 = 20. Return only x.","domain":"math","reference_answer":"5","grader":{"type":"numeric","tolerance":0.0},"split":"train","tags":["algebra"]}
{"task_id":"math-005","prompt":"A triangle has angles 50 and 60 degrees. Return the third angle as a number.","domain":"math","reference_answer":"70","grader":{"type":"numeric","tolerance":0.0},"split":"train","tags":["geometry"]}
{"task_id":"math-006","prompt":"Compute 2 to the power 10. Return only the number.","domain":"math","reference_answer":"1024","grader":{"type":"numeric","tolerance":0.0},"split":"train","tags":["arithmetic"]}
{"task_id":"code-001","prompt":"Which Python keyword starts a function definition? Answer with the keyword.","domain":"code","reference_answer":"def","grader":{"type":"contains"},"split":"train","tags":["python"]}
{"task_id":"code-002","prompt":"What is the conventional filename for Python package build metadata using PEP 621?","domain":"code","reference_answer":"pyproject.toml","grader":{"type":"contains"},"split":"train","tags":["python","packaging"]}
{"task_id":"code-003","prompt":"Which Git command displays the working tree status?","domain":"code","reference_answer":"git status","grader":{"type":"contains"},"split":"train","tags":["git"]}
{"task_id":"code-004","prompt":"Which SQL keyword removes duplicate rows from a SELECT result?","domain":"code","reference_answer":"DISTINCT","grader":{"type":"contains"},"split":"train","tags":["sql"]}
{"task_id":"code-005","prompt":"Name the HTTP method normally used to retrieve a resource.","domain":"code","reference_answer":"GET","grader":{"type":"contains"},"split":"train","tags":["http"]}
{"task_id":"code-006","prompt":"Which shell command prints the current working directory?","domain":"code","reference_answer":"pwd","grader":{"type":"contains"},"split":"train","tags":["shell"]}
{"task_id":"general-001","prompt":"What is the capital of France?","domain":"general","reference_answer":"Paris","grader":{"type":"contains"},"split":"train","tags":["geography"]}
{"task_id":"general-002","prompt":"Which planet is known as the Red Planet?","domain":"general","reference_answer":"Mars","grader":{"type":"contains"},"split":"train","tags":["science"]}
{"task_id":"general-003","prompt":"Who wrote Hamlet?","domain":"general","reference_answer":"Shakespeare","grader":{"type":"contains"},"split":"train","tags":["literature"]}
{"task_id":"general-004","prompt":"What gas do plants absorb from the atmosphere during photosynthesis?","domain":"general","reference_answer":"carbon dioxide","grader":{"type":"contains"},"split":"train","tags":["science"]}
{"task_id":"general-005","prompt":"What is the largest ocean on Earth?","domain":"general","reference_answer":"Pacific","grader":{"type":"contains"},"split":"train","tags":["geography"]}
{"task_id":"general-006","prompt":"Which language is primarily spoken in Brazil?","domain":"general","reference_answer":"Portuguese","grader":{"type":"contains"},"split":"train","tags":["language"]}
{"task_id":"math-val-001","prompt":"Compute 11 squared. Return only the number.","domain":"math","reference_answer":"121","grader":{"type":"numeric","tolerance":0.0},"split":"validation","tags":["arithmetic"]}
{"task_id":"math-val-002","prompt":"Solve 2x = 18. Return only x.","domain":"math","reference_answer":"9","grader":{"type":"numeric","tolerance":0.0},"split":"validation","tags":["algebra"]}
{"task_id":"code-val-001","prompt":"Which Python keyword creates an anonymous function?","domain":"code","reference_answer":"lambda","grader":{"type":"contains"},"split":"validation","tags":["python"]}
{"task_id":"code-val-002","prompt":"Which HTTP status code means Not Found? Return the number.","domain":"code","reference_answer":"404","grader":{"type":"contains"},"split":"validation","tags":["http"]}
{"task_id":"general-val-001","prompt":"What is the capital of Japan?","domain":"general","reference_answer":"Tokyo","grader":{"type":"contains"},"split":"validation","tags":["geography"]}
{"task_id":"general-val-002","prompt":"Which element has the chemical symbol O?","domain":"general","reference_answer":"oxygen","grader":{"type":"contains"},"split":"validation","tags":["science"]}
{"task_id":"math-test-001","prompt":"Compute 15 percent of 200. Return only the number.","domain":"math","reference_answer":"30","grader":{"type":"numeric","tolerance":0.0},"split":"test","tags":["percent"]}
{"task_id":"math-test-002","prompt":"Compute 7 cubed. Return only the number.","domain":"math","reference_answer":"343","grader":{"type":"numeric","tolerance":0.0},"split":"test","tags":["arithmetic"]}
{"task_id":"code-test-001","prompt":"Which command initializes a new Git repository?","domain":"code","reference_answer":"git init","grader":{"type":"contains"},"split":"test","tags":["git"]}
{"task_id":"code-test-002","prompt":"Which Python built-in returns the number of items in a collection?","domain":"code","reference_answer":"len","grader":{"type":"contains"},"split":"test","tags":["python"]}
{"task_id":"general-test-001","prompt":"What is the capital of Canada?","domain":"general","reference_answer":"Ottawa","grader":{"type":"contains"},"split":"test","tags":["geography"]}
{"task_id":"general-test-002","prompt":"Which instrument measures temperature?","domain":"general","reference_answer":"thermometer","grader":{"type":"contains"},"split":"test","tags":["science"]}