Files
Mofox-Core/llm_tool_benchmark_results.json
2025-04-29 01:49:51 +08:00

145 lines
4.8 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"测试时间": "2025-04-28 14:12:36",
"测试迭代次数": 10,
"不使用工具调用": {
"平均耗时": 4.596814393997192,
"最短耗时": 2.957131862640381,
"最长耗时": 10.121938705444336,
"标准差": 2.1705468730949593,
"所有耗时": [
3.18,
4.65,
10.12,
3.5,
4.46,
4.24,
3.23,
6.2,
2.96,
3.42
]
},
"不使用工具调用_详细响应": [
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"content\": \"怎么啦?\",\n \"emoji_query\": \"友好地询问\"\n}\n```",
"推理内容摘要": ""
},
{
"内容摘要": "decide_reply_action(\n action=\"text_reply\",\n reasoning=\"千石连续两次叫了我的名字,显然是想引起我的注意或有事要说,作为礼貌应当回应\",\n emoji_query=\"友善的回应\"\n)",
"推理内容摘要": ""
},
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"content\": \"怎么啦?我在呢~\",\n \"emoji_query\": \"友好的询问\",\n \"reasoning\": \"由于对方连续两次提到我的名字,显然是想与我交流,应当及时给予友好回应避免冷场\"\n}\n```",
"推理内容摘要": ""
},
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"content\": \"在呢在呢~怎么啦?\",\n \"emoji_query\": \"好奇的回应\"\n}\n```",
"推理内容摘要": ""
},
{
"内容摘要": "decide_reply_action(\n action=\"text_reply\",\n reasoning=\"千石连续两次提到我的名字,显然需要我回应。文字回复更正式且能明确表示我在关注他的信息。\",\n emoji_query=\"友好的回应\"\n)",
"推理内容摘要": ""
},
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"reasoning\": \"千石连续两次提到我的名字,显然是需要我的回应。作为日常交流,应该给予友善简短的答复。\",\n \"emoji_query\": \"疑惑的歪头\"\n}\n```",
"推理内容摘要": ""
},
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"content\": \"咋啦千石~\",\n \"emoji_query\": \"好奇的询问\"\n}\n```",
"推理内容摘要": ""
},
{
"内容摘要": "decide_reply_action\n```json\n{\n \"action\": \"text_reply\",\n \"content\": \"我在呢~怎么啦?\",\n \"emoji_query\": \"友好的关心\",\n \"reasoning\": \"千石连续两次呼唤我的名字显然是有事情要找我或想引起我的注意。根据回复原则2有人提到你但未回应应该用友善的文字进行回应并附上表达关心的表情符号来延...",
"推理内容摘要": ""
},
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"content\": \"千石怎么啦~\",\n \"emoji_query\": \"好奇的探询\"\n}\n```",
"推理内容摘要": ""
},
{
"内容摘要": "```json\n{\n \"action\": \"text_reply\",\n \"content\": \"怎么啦?突然叫我两次\",\n \"emoji_query\": \"好奇的疑问\"\n}\n```",
"推理内容摘要": ""
}
],
"使用工具调用": {
"平均耗时": 8.139546775817871,
"最短耗时": 4.9980738162994385,
"最长耗时": 18.803313732147217,
"标准差": 4.008772720760647,
"所有耗时": [
5.81,
18.8,
6.06,
8.06,
10.07,
6.34,
7.9,
6.66,
5.0,
6.69
]
},
"使用工具调用_详细响应": [
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
},
{
"内容摘要": "",
"推理内容摘要": "",
"工具调用数量": 0,
"工具调用详情": []
}
],
"差异百分比": 77.07
}