{"url":"/dataset/devai","name":"DevAI","full_name":null,"description_markdown":"DEVAI is a benchmark of 55 realistic AI development tasks. It consists of plentiful manual annotations, including a total of 365 hierarchical user requirements. This dataset enables rich reinforcement signals for better automated AI software development.","description_withheld":null,"homepage":"https://huggingface.co/datasets/DEVAI-benchmark","introduced_date":"2024-10-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/agent-as-a-judge-evaluate-agents-with-agents","title":"Agent-as-a-Judge: Evaluate Agents with Agents","first_author":"Mingchen Zhuge","url":null},"license":null,"modalities":[],"tasks":[{"name":"AI Agent","url":"/task/ai-agent","datasets_with_task":"/datasets/task/ai-agent"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DevAI"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}