Initial commit: 让多个 AI 智能体通过文件总线在共享聊天室里互相 @、协作与交接任务

This commit is contained in:
WpyQwq
2026-09-19 11:52:42 +08:00
commit 103f0b32f5
28 changed files with 5834 additions and 0 deletions
+207
View File
@@ -0,0 +1,207 @@
{
"at": "2026-09-18T15:28:16.430Z",
"tasks": [
{
"id": "Q1",
"expect": "0.05(或「五分」)",
"q": "球拍和球一共 1.10 元,球拍比球贵 1.00 元。球多少钱?"
},
{
"id": "Q2",
"expect": "143",
"q": "小于 1000 的正整数里,有多少个满足「除以 7 余 3」?"
},
{
"id": "Q3",
"expect": "3",
"q": "Python 表达式 len(list(range(10))[2:5]) 的值是多少?"
},
{
"id": "Q4",
"expect": "不能",
"q": "已知「所有 A 都是 B」且「有些 B 是 C」。能否必然推出「有些 A 是 C」?只回答 能 或 不能。"
},
{
"id": "Q5",
"expect": "4412",
"q": "下面这段文本里出现过一次「构建编号」,它的数字是多少?\n\n这条记录只用于填充上下文,不包含任何需要记忆的信息。例行巡检没有发现异常,指标都在阈值内。文档结构保持"
}
],
"results": [
{
"model": "opencode/big-pickle",
"ok": true,
"ms": 6270,
"score": 5,
"total": 5,
"per": {
"Q1": {
"answer": "0.05",
"expect": "0.05(或「五分」)",
"pass": true
},
"Q2": {
"answer": "143",
"expect": "143",
"pass": true
},
"Q3": {
"answer": "3",
"expect": "3",
"pass": true
},
"Q4": {
"answer": "不能",
"expect": "不能",
"pass": true
},
"Q5": {
"answer": "4412",
"expect": "4412",
"pass": true
}
},
"raw": "Q1) 0.05\nQ2) 143\nQ3) 3\nQ4) 不能\nQ5) 4412"
},
{
"model": "opencode/ling-3.0-flash-fin-free",
"ok": true,
"ms": 6635,
"score": 5,
"total": 5,
"per": {
"Q1": {
"answer": "0.05",
"expect": "0.05(或「五分」)",
"pass": true
},
"Q2": {
"answer": "143",
"expect": "143",
"pass": true
},
"Q3": {
"answer": "3",
"expect": "3",
"pass": true
},
"Q4": {
"answer": "不能",
"expect": "不能",
"pass": true
},
"Q5": {
"answer": "4412",
"expect": "4412",
"pass": true
}
},
"raw": "Q1) 0.05\nQ2) 143\nQ3) 3\nQ4) 不能\nQ5) 4412"
},
{
"model": "opencode/nemotron-3.5-lightning-free",
"ok": true,
"ms": 16481,
"score": 5,
"total": 5,
"per": {
"Q1": {
"answer": "0.05",
"expect": "0.05(或「五分」)",
"pass": true
},
"Q2": {
"answer": "143",
"expect": "143",
"pass": true
},
"Q3": {
"answer": "3",
"expect": "3",
"pass": true
},
"Q4": {
"answer": "不能",
"expect": "不能",
"pass": true
},
"Q5": {
"answer": "4412",
"expect": "4412",
"pass": true
}
},
"raw": "Q1) 0.05\nQ2) 143\nQ3) 3\nQ4) 不能\nQ5) 4412"
},
{
"model": "opencode/nemotron-3-ultra-free",
"ok": true,
"ms": 57671,
"score": 5,
"total": 5,
"per": {
"Q1": {
"answer": "0.05",
"expect": "0.05(或「五分」)",
"pass": true
},
"Q2": {
"answer": "143",
"expect": "143",
"pass": true
},
"Q3": {
"answer": "3",
"expect": "3",
"pass": true
},
"Q4": {
"answer": "不能",
"expect": "不能",
"pass": true
},
"Q5": {
"answer": "4412",
"expect": "4412",
"pass": true
}
},
"raw": "Q1) 0.05\nQ2) 143\nQ3) 3\nQ4) 不能\nQ5) 4412"
},
{
"model": "opencode/mimo-v2.5-free",
"ok": true,
"ms": 19624,
"score": 4,
"total": 5,
"per": {
"Q1": {
"answer": "5分",
"expect": "0.05(或「五分」)",
"pass": false
},
"Q2": {
"answer": "143个",
"expect": "143",
"pass": true
},
"Q3": {
"answer": "3",
"expect": "3",
"pass": true
},
"Q4": {
"answer": "不能",
"expect": "不能",
"pass": true
},
"Q5": {
"answer": "4412",
"expect": "4412",
"pass": true
}
},
"raw": "Q1) 5分\nQ2) 143个\nQ3) 3\nQ4) 不能\nQ5) 4412"
}
]
}