{"ok":true,"trend":{"id":668841,"platform":"hn","region":"global","key":"dogbench: the first user-facing docs generation benchmark. no model scores >50%","title":"DoGBench: The first user-facing docs generation benchmark. No model scores >50%","url":"https://dogbench.ai/","first_seen":"2026-10-02T00:05:39.675951Z","last_seen":"2026-10-02T00:20:39.673916Z","last_rank":29,"peak_rank":29,"last_volume":5,"peak_volume":5,"seen_count":2,"score":0.9859375,"category_hint":null,"section":null,"category":null,"summary":"DoGBench has been introduced as the first benchmark aimed at evaluating how well AI models generate user-facing documentation. Early results show that no model scores above 50%, a surprisingly low ceiling that is drawing attention. Developers on Hacker News are discussing what the weak performance says about the gap between coding assistants and genuinely usable documentation output.","why":"New benchmark results reveal that AI models are far worse at generating documentation than at other tasks, sparking debate","tone":"neutral","entities":["DoGBench","Hacker News","AI language models"],"summarized_at":"2026-10-02T00:07:50.642571Z","meta":{"lang":"en","link":"https://dogbench.ai/","hn_id":"49928118","comments":2},"nw":null,"promo":null,"kind":null,"importance":null,"hidden":false,"hide_reason":null,"judged_at":null,"title_en":"DoGBench launches as first docs generation benchmark, AI falls short","timeline":[{"captured_at":"2026-10-02T00:05:39.675951Z","rank":30,"volume":4},{"captured_at":"2026-10-02T00:20:39.673916Z","rank":29,"volume":5}],"posts":[{"platform":"hn","url":"https://news.ycombinator.com/item?id=49928118","author":"prithvi2206","title":"DoGBench: The first user-facing docs generation benchmark. No model scores >50%","snippet":null,"posted_at":"2026-10-01T23:10:32Z","likes":5}],"elsewhere":[],"window":"7d"}}