- 规则库 3.6→3.8.1(542→548 条):剪枝上锁、R-杂-38 从格临界双轨、 R-事-10~13 冲刑方向判别、R-禁-23 自造必要条件之禁 - 排盘修复随 3.6.2 已发:港澳时区夏令时双向误拨、晚子时双重换日 - 新增 评测/ 目录(BaziQA 题答分离、判分工具、记分卡、with/without-skill 对照) 与 scripts/query_rules.py 条款检索;ZIPEC_EVAL 评测额度豁免 - manifest 重建并重新签名;VERSION 保持 3.6.2,不发版不打 tag
49 lines
1.9 KiB
JSON
49 lines
1.9 KiB
JSON
{
|
||
"model": "deepseek-v4-flash",
|
||
"skill_mode": "without-skill",
|
||
"skill_version": "3.6.2",
|
||
"eval_date": "2026-10-13",
|
||
"benchmark": "BaziQA-全球算命师大赛",
|
||
"overall": {"total": 200, "correct": 71, "accuracy": 35.5, "no_answer": 0},
|
||
"baseline": {
|
||
"name": "官方基线(Gemini)",
|
||
"overall": {"total": 200, "correct": 69, "accuracy": 34.5},
|
||
"per_contest": {
|
||
"contest8_2021": 27.5,
|
||
"contest8_2022": 40.0,
|
||
"contest8_2023": 27.5,
|
||
"contest8_2024": 35.0,
|
||
"contest8_2025": 42.5
|
||
},
|
||
"per_dimension": {
|
||
"流年运势": 40.5,
|
||
"感情": 36.7,
|
||
"六亲": 27.6,
|
||
"事业": 24.0,
|
||
"性格": 45.0,
|
||
"学业": 41.7,
|
||
"财富": 30.8,
|
||
"健康": 23.1,
|
||
"其他": 50.0
|
||
}
|
||
},
|
||
"per_contest": {
|
||
"contest8_2021": {"total": 40, "correct": 17, "accuracy": 42.5, "no_answer": 0},
|
||
"contest8_2022": {"total": 40, "correct": 18, "accuracy": 45.0, "no_answer": 0},
|
||
"contest8_2023": {"total": 40, "correct": 6, "accuracy": 15.0, "no_answer": 0},
|
||
"contest8_2024": {"total": 40, "correct": 19, "accuracy": 47.5, "no_answer": 0},
|
||
"contest8_2025": {"total": 40, "correct": 11, "accuracy": 27.5, "no_answer": 0}
|
||
},
|
||
"per_dimension": {
|
||
"流年运势": {"total": 37, "correct": 11, "accuracy": 29.7, "no_answer": 0},
|
||
"感情": {"total": 49, "correct": 13, "accuracy": 26.5, "no_answer": 0},
|
||
"六亲": {"total": 29, "correct": 12, "accuracy": 41.4, "no_answer": 0},
|
||
"事业": {"total": 25, "correct": 10, "accuracy": 40.0, "no_answer": 0},
|
||
"性格": {"total": 20, "correct": 11, "accuracy": 55.0, "no_answer": 0},
|
||
"学业": {"total": 12, "correct": 5, "accuracy": 41.7, "no_answer": 0},
|
||
"财富": {"total": 13, "correct": 3, "accuracy": 23.1, "no_answer": 0},
|
||
"健康": {"total": 13, "correct": 5, "accuracy": 38.5, "no_answer": 0},
|
||
"其他": {"total": 2, "correct": 1, "accuracy": 50.0, "no_answer": 0}
|
||
}
|
||
}
|