{ "version": "2026-10-01", "license": "CC BY 4.0", "attribution": "Fulin Labs Chinese Text Analyzer reference samples", "source": "https://fulinlabs.com/tools/chinese-text-analyzer/#reference-benchmark", "scope": "Original diagnostic examples, not a representative corpus or a proficiency test.", "samples": [ { "id": "everyday-simplified", "label": "Everyday sentence", "text": "我们明天去学校学习中文。", "note": "Short everyday sentence; no assigned teaching level.", "textSha256": "2ae399739e60c240a397525a52402b0719f67acf0891cc5f29c27993fa67ff48", "analysis": { "total": 12, "han": 11, "unique": 10, "traditional": 0, "rows": [ { "level": 1, "count": 10, "share": 0.9090909090909091, "cumulative": 0.9090909090909091 }, { "level": 2, "count": 0, "share": 0, "cumulative": 0.9090909090909091 }, { "level": 3, "count": 1, "share": 0.09090909090909091, "cumulative": 1 }, { "level": 4, "count": 0, "share": 0, "cumulative": 1 }, { "level": 5, "count": 0, "share": 0, "cumulative": 1 }, { "level": 6, "count": 0, "share": 0, "cumulative": 1 } ], "assigned": { "level": 1, "count": 10, "share": 0.9090909090909091, "cumulative": 0.9090909090909091 }, "against": 1, "above": [ [ "文", 1 ] ], "matched": [ "去", "学习", "学校", "我们", "明天", "中文" ] } }, { "id": "everyday-traditional", "label": "Traditional counterpart", "text": "我們明天去學校學習中文。", "note": "Same sentence in traditional characters; compare the six coverage rows.", "textSha256": "e1321da991b532a0800b7cb6729158377ed54ca6c4e3961336d0b32ac6f1839a", "analysis": { "total": 12, "han": 11, "unique": 10, "traditional": 4, "rows": [ { "level": 1, "count": 10, "share": 0.9090909090909091, "cumulative": 0.9090909090909091 }, { "level": 2, "count": 0, "share": 0, "cumulative": 0.9090909090909091 }, { "level": 3, "count": 1, "share": 0.09090909090909091, "cumulative": 1 }, { "level": 4, "count": 0, "share": 0, "cumulative": 1 }, { "level": 5, "count": 0, "share": 0, "cumulative": 1 }, { "level": 6, "count": 0, "share": 0, "cumulative": 1 } ], "assigned": { "level": 1, "count": 10, "share": 0.9090909090909091, "cumulative": 0.9090909090909091 }, "against": 1, "above": [ [ "文", 1 ] ], "matched": [ "去", "学习", "学校", "我们", "明天", "中文" ] } }, { "id": "commute", "label": "Commute and reading", "text": "我每天早上喝一杯咖啡，然后坐地铁去上班。路上我会用手机看一篇中文新闻，遇到不认识的词就先猜意思，晚上再复习一次。", "note": "The analyzer’s existing sample passage.", "textSha256": "0fa64416cd75c33d817ddac1eb04745472efc8f9f078d61333d7f2e4a4e8fb42", "analysis": { "total": 56, "han": 51, "unique": 45, "traditional": 0, "rows": [ { "level": 1, "count": 26, "share": 0.5098039215686274, "cumulative": 0.5098039215686274 }, { "level": 2, "count": 15, "share": 0.29411764705882354, "cumulative": 0.803921568627451 }, { "level": 3, "count": 8, "share": 0.1568627450980392, "cumulative": 0.9607843137254902 }, { "level": 4, "count": 2, "share": 0.0392156862745098, "cumulative": 1 }, { "level": 5, "count": 0, "share": 0, "cumulative": 1 }, { "level": 6, "count": 0, "share": 0, "cumulative": 1 } ], "assigned": { "level": 3, "count": 8, "share": 0.1568627450980392, "cumulative": 0.9607843137254902 }, "against": 3, "above": [ [ "猜", 1 ], [ "篇", 1 ] ], "matched": [ "一", "上", "不", "会", "去", "喝", "坐", "我", "的", "看", "认识", "上班", "再", "咖啡", "就", "意思", "手机", "早上", "晚上", "次", "每", "路", "中文", "先", "地铁", "复习", "新闻", "然后", "用", "遇到", "猜", "篇" ] } }, { "id": "technical", "label": "Technical vocabulary", "text": "研究人员用机器学习分析基因序列，发现蛋白质结构发生了变化。", "note": "Constructed technical example, not a representative science corpus.", "textSha256": "2c1b7d0fefb2db5ae21fc12c27a7cc582faa1ec911afb66e2e3bfccaa6041e20", "analysis": { "total": 29, "han": 27, "unique": 26, "traditional": 0, "rows": [ { "level": 1, "count": 8, "share": 0.2962962962962963, "cumulative": 0.2962962962962963 }, { "level": 2, "count": 4, "share": 0.14814814814814814, "cumulative": 0.4444444444444444 }, { "level": 3, "count": 6, "share": 0.2222222222222222, "cumulative": 0.6666666666666666 }, { "level": 4, "count": 6, "share": 0.2222222222222222, "cumulative": 0.8888888888888888 }, { "level": 5, "count": 3, "share": 0.1111111111111111, "cumulative": 1 }, { "level": 6, "count": 0, "share": 0, "cumulative": 1 } ], "assigned": { "level": 5, "count": 3, "share": 0.1111111111111111, "cumulative": 1 }, "against": 5, "above": [], "matched": [ "了", "学习", "发现", "变化", "用", "发生", "研究", "人员", "分析", "机器", "结构", "基因", "蛋白质" ] } }, { "id": "repetition", "label": "Repetition and one rare character", "text": "我我我我我我我我我龘", "note": "Nine familiar occurrences can reach 90% despite one unknown character.", "textSha256": "6b6f4fa4f17c7d2d1f686d1b1a84f806b62a92a45357d46f56c5c5649aa78f06", "analysis": { "total": 10, "han": 10, "unique": 2, "traditional": 0, "rows": [ { "level": 1, "count": 9, "share": 0.9, "cumulative": 0.9 }, { "level": 2, "count": 0, "share": 0, "cumulative": 0.9 }, { "level": 3, "count": 0, "share": 0, "cumulative": 0.9 }, { "level": 4, "count": 0, "share": 0, "cumulative": 0.9 }, { "level": 5, "count": 0, "share": 0, "cumulative": 0.9 }, { "level": 6, "count": 0, "share": 0, "cumulative": 0.9 } ], "assigned": { "level": 1, "count": 9, "share": 0.9, "cumulative": 0.9 }, "against": 1, "above": [ [ "龘", 1 ] ], "matched": [ "我" ] } }, { "id": "rare-only", "label": "Rare character only", "text": "龘", "note": "A Han character outside the bundled lists.", "textSha256": "90aef66721f7baf348bc74d4f586b17f97f389eb1ecaab83e99c911948470dff", "analysis": { "total": 1, "han": 1, "unique": 1, "traditional": 0, "rows": [ { "level": 1, "count": 0, "share": 0, "cumulative": 0 }, { "level": 2, "count": 0, "share": 0, "cumulative": 0 }, { "level": 3, "count": 0, "share": 0, "cumulative": 0 }, { "level": 4, "count": 0, "share": 0, "cumulative": 0 }, { "level": 5, "count": 0, "share": 0, "cumulative": 0 }, { "level": 6, "count": 0, "share": 0, "cumulative": 0 } ], "against": 6, "above": [ [ "龘", 1 ] ], "matched": [] } }, { "id": "mixed", "label": "Chinese with Latin text and emoji", "text": "我们学习中文。Hello 2026! 😊", "note": "Non-Han characters count toward total length, not HSK coverage.", "textSha256": "c1a2e7cc4dff0a51391a910a6654e436eaf0588eb1a961ba6a155027e8405a51", "analysis": { "total": 20, "han": 6, "unique": 6, "traditional": 0, "rows": [ { "level": 1, "count": 5, "share": 0.8333333333333334, "cumulative": 0.8333333333333334 }, { "level": 2, "count": 0, "share": 0, "cumulative": 0.8333333333333334 }, { "level": 3, "count": 1, "share": 0.16666666666666666, "cumulative": 1 }, { "level": 4, "count": 0, "share": 0, "cumulative": 1 }, { "level": 5, "count": 0, "share": 0, "cumulative": 1 }, { "level": 6, "count": 0, "share": 0, "cumulative": 1 } ], "assigned": { "level": 3, "count": 1, "share": 0.16666666666666666, "cumulative": 1 }, "against": 3, "above": [], "matched": [ "学习", "我们", "中文" ] } }, { "id": "no-han", "label": "No Chinese characters", "text": "Hello 2026! 😊", "note": "No Han means no assigned level, rather than above HSK 6.", "textSha256": "c1e86fab12387004957cfebaa8a4f03fd75a9e388d817b7416e20108e7cb3837", "analysis": { "total": 13, "han": 0, "unique": 0, "traditional": 0, "rows": [ { "level": 1, "count": 0, "share": 0, "cumulative": 0 }, { "level": 2, "count": 0, "share": 0, "cumulative": 0 }, { "level": 3, "count": 0, "share": 0, "cumulative": 0 }, { "level": 4, "count": 0, "share": 0, "cumulative": 0 }, { "level": 5, "count": 0, "share": 0, "cumulative": 0 }, { "level": 6, "count": 0, "share": 0, "cumulative": 0 } ], "against": 6, "above": [], "matched": [] } } ], "method": "Lowest HSK 2012 level covering at least 90% of Han character occurrences; no reader level selected.", "threshold": 0.9, "wordListSource": "https://hskhsk.com/word-lists.html", "wordListSha256": "4ec3d6f09877204385ff5fbfc4b71e1fa41b09f32b97fd4fec1ed493dc57bf69" }