Files
ai-group-chat/tools/shootout2-result.json
T

205 lines
5.8 KiB
JSON

{
"at": "2026-09-18T15:23:15.243Z",
"results": [
{
"model": "opencode/big-pickle",
"ok": true,
"ms": 16526,
"score": 6,
"max": 7,
"per": {
"H1": {
"pass": 1,
"max": 1,
"answer": "21",
"expect": "21"
},
"H2": {
"pass": 1,
"max": 1,
"answer": "B",
"expect": "B"
},
"H3": {
"pass": 1,
"max": 1,
"answer": "4=2 5=4",
"expect": "4=2 5=4"
},
"H4": {
"pass": 3,
"max": 3,
"answer": "缓存=Redis 7 灰度=15% 回滚=RB-3390",
"expect": "缓存=Redis 7 灰度=15% 回滚=RB-3390"
},
"H5": {
"pass": 0,
"max": 1,
"answer": "AssertionError [ERR_ASSERTION]: n 超过长度时应返回全部\r",
"expect": "可运行的 lastN(会真的跑断言)"
}
},
"raw": "H1) 21\nH2) B\nH3) 4=2 5=4\nH4) 缓存=Redis 7 灰度=15% 回滚=RB-3390\nH5) \n```js\nfunction lastN(arr, n) {\n const out = [];\n for (let i = arr.length - n; i < arr.length; i++) {\n out.push(arr[i]);\n }\n return out;\n}\n```"
},
{
"model": "opencode/nemotron-3-ultra-free",
"ok": true,
"ms": 94384,
"score": 6,
"max": 7,
"per": {
"H1": {
"pass": 1,
"max": 1,
"answer": "21",
"expect": "21"
},
"H2": {
"pass": 1,
"max": 1,
"answer": "B",
"expect": "B"
},
"H3": {
"pass": 1,
"max": 1,
"answer": "4=2 5=4",
"expect": "4=2 5=4"
},
"H4": {
"pass": 3,
"max": 3,
"answer": "缓存=Redis 7 灰度=15% 回滚=RB-3390",
"expect": "缓存=Redis 7 灰度=15% 回滚=RB-3390"
},
"H5": {
"pass": 0,
"max": 1,
"answer": "AssertionError [ERR_ASSERTION]: n 超过长度时应返回全部\r",
"expect": "可运行的 lastN(会真的跑断言)"
}
},
"raw": "H1) 21\nH2) B\nH3) 4=2 5=4\nH4) 缓存=Redis 7 灰度=15% 回滚=RB-3390\nH5) \nfunction lastN(arr, n) {\n const out = [];\n for (let i = arr.length - n; i < arr.length; i++) {\n out.push(arr[i]);\n }\n return out;\n}"
},
{
"model": "opencode/nemotron-3.5-lightning-free",
"ok": true,
"ms": 103197,
"score": 6,
"max": 7,
"per": {
"H1": {
"pass": 1,
"max": 1,
"answer": "21",
"expect": "21"
},
"H2": {
"pass": 1,
"max": 1,
"answer": "B",
"expect": "B"
},
"H3": {
"pass": 1,
"max": 1,
"answer": "4=2 5=4",
"expect": "4=2 5=4"
},
"H4": {
"pass": 3,
"max": 3,
"answer": "缓存=Redis 7 灰度=15% 回滚=RB-3390",
"expect": "缓存=Redis 7 灰度=15% 回滚=RB-3390"
},
"H5": {
"pass": 0,
"max": 1,
"answer": "没找到函数定义",
"expect": "可运行的 lastN(会真的跑断言)"
}
},
"raw": "H1) 21\nH2) B\nH3) 4=2 5=4\nH4) 缓存=Redis 7 灰度=15% 回滚=RB-3390\nH5) function lastN(arr, n) { const out = []; for (let i = arr.length - n; i < arr.length; i++) { out.push(arr[i]); } return out; }"
},
{
"model": "opencode/ling-3.0-flash-fin-free",
"ok": true,
"ms": 19138,
"score": 5,
"max": 7,
"per": {
"H1": {
"pass": 0,
"max": 1,
"answer": "20",
"expect": "21"
},
"H2": {
"pass": 1,
"max": 1,
"answer": "B",
"expect": "B"
},
"H3": {
"pass": 1,
"max": 1,
"answer": "4=2 5=4",
"expect": "4=2 5=4"
},
"H4": {
"pass": 3,
"max": 3,
"answer": "缓存=Redis 7 灰度=15% 回滚=RB-3390",
"expect": "缓存=Redis 7 灰度=15% 回滚=RB-3390"
},
"H5": {
"pass": 0,
"max": 1,
"answer": "AssertionError [ERR_ASSERTION]: lastN([1..5],2) 应为 [4,5]\r",
"expect": "可运行的 lastN(会真的跑断言)"
}
},
"raw": "H1) 20\nH2) B\nH3) 4=2 5=4\nH4) 缓存=Redis 7 灰度=15% 回滚=RB-3390\nH5)\n```js\nfunction lastN(arr, n) {\n const out = [];\n for (let i = arr.length - 1; i >= arr.length - n; i--) {\n out.push(arr[i]);\n }\n return out;\n}\n```"
},
{
"model": "opencode/mimo-v2.5-free",
"ok": true,
"ms": 26756,
"score": 5,
"max": 7,
"per": {
"H1": {
"pass": 0,
"max": 1,
"answer": "20",
"expect": "21"
},
"H2": {
"pass": 1,
"max": 1,
"answer": "B",
"expect": "B"
},
"H3": {
"pass": 1,
"max": 1,
"answer": "4=2 5=4",
"expect": "4=2 5=4"
},
"H4": {
"pass": 3,
"max": 3,
"answer": "缓存=Redis 7 灰度=15% 回滚=RB-3390",
"expect": "缓存=Redis 7 灰度=15% 回滚=RB-3390"
},
"H5": {
"pass": 0,
"max": 1,
"answer": "AssertionError [ERR_ASSERTION]: lastN([1..5],2) 应为 [4,5]\r",
"expect": "可运行的 lastN(会真的跑断言)"
}
},
"raw": "H1) 20\n\nH2) B\n\nH3) 4=2 5=4\n\nH4) 缓存=Redis 7 灰度=15% 回滚=RB-3390\n\nH5) function lastN(arr, n) {\n const out = [];\n for (let i = arr.length - 1; i >= arr.length - n; i--) {\n out.push(arr[i]);\n }\n return out;\n}"
}
]
}