moxiaonian
1a0eed1999
- 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
129 lines
2.6 KiB
JSON
129 lines
2.6 KiB
JSON
{
|
||
"model": "qoder-agent",
|
||
"skill_mode": "with-skill",
|
||
"skill_version": "3.6.2-未发版（规则库 3.7）",
|
||
"eval_date": "2026-10-13",
|
||
"benchmark": "BaziQA-全球算命师大赛",
|
||
"overall": {
|
||
"total": 200,
|
||
"correct": 79,
|
||
"accuracy": 39.5,
|
||
"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": 16,
|
||
"no_answer": 0,
|
||
"accuracy": 40.0
|
||
},
|
||
"contest8_2022": {
|
||
"total": 40,
|
||
"correct": 15,
|
||
"no_answer": 0,
|
||
"accuracy": 37.5
|
||
},
|
||
"contest8_2023": {
|
||
"total": 40,
|
||
"correct": 15,
|
||
"no_answer": 0,
|
||
"accuracy": 37.5
|
||
},
|
||
"contest8_2024": {
|
||
"total": 40,
|
||
"correct": 19,
|
||
"no_answer": 0,
|
||
"accuracy": 47.5
|
||
},
|
||
"contest8_2025": {
|
||
"total": 40,
|
||
"correct": 14,
|
||
"no_answer": 0,
|
||
"accuracy": 35.0
|
||
}
|
||
},
|
||
"per_dimension": {
|
||
"流年运势": {
|
||
"total": 37,
|
||
"correct": 15,
|
||
"no_answer": 0,
|
||
"accuracy": 40.5
|
||
},
|
||
"感情": {
|
||
"total": 49,
|
||
"correct": 16,
|
||
"no_answer": 0,
|
||
"accuracy": 32.7
|
||
},
|
||
"六亲": {
|
||
"total": 29,
|
||
"correct": 15,
|
||
"no_answer": 0,
|
||
"accuracy": 51.7
|
||
},
|
||
"事业": {
|
||
"total": 25,
|
||
"correct": 10,
|
||
"no_answer": 0,
|
||
"accuracy": 40.0
|
||
},
|
||
"性格": {
|
||
"total": 20,
|
||
"correct": 8,
|
||
"no_answer": 0,
|
||
"accuracy": 40.0
|
||
},
|
||
"学业": {
|
||
"total": 12,
|
||
"correct": 5,
|
||
"no_answer": 0,
|
||
"accuracy": 41.7
|
||
},
|
||
"财富": {
|
||
"total": 13,
|
||
"correct": 5,
|
||
"no_answer": 0,
|
||
"accuracy": 38.5
|
||
},
|
||
"健康": {
|
||
"total": 13,
|
||
"correct": 4,
|
||
"no_answer": 0,
|
||
"accuracy": 30.8
|
||
},
|
||
"其他": {
|
||
"total": 2,
|
||
"correct": 1,
|
||
"no_answer": 0,
|
||
"accuracy": 50.0
|
||
}
|
||
},
|
||
"notes": "判分：评测/工具/run_eval.py；求解留档：评测/ai答案/qoder-agent/with-skill/（41 位命主，每位新开无上下文子代理，真太阳时主盘 + 双盘纪律）；技能副本 /tmp/skill_bench（rsync 自母版，排除 评测/ 与 .git，故物理隔绝答案键）+ extend_cities.py 地点扩展；全程 ZIPEC_EVAL=1，副本 data/ 仅 cities.json、无 .license.json，零额度消耗；官方基线口径见 试题/BaziQA-全球算命师大赛/SOURCE.md"
|
||
}
|