历史详情

Run ID: 20260831-062104-315e9cd3

返回历史

测试结果

Run ID: 20260831-062104-315e9cd3

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟2898 ms
P95 / Tokens6455 / 4739
渠道模型成功失败成功率失败率稳定性平均延迟 msP95 msTokens首个错误
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1130 1148 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1146 1243 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1207 1540 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1269 1321 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1721 2159 383
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1803 1952 386
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1974 2064 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2849 3126 79
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4661 5158 544
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4874 5310 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5369 6455 898
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 6770 7652 670
MiniMax H3 Context IR MiniMax-H3 0/3 3/3 0.0% 100.0% 不稳定 - - 0 HTTP 400: binding: expr_path=content, cause=missing required parameter
pixflow-gemini-3.1-pro-preview gemini-3.1-pro-preview 0/3 3/3 0.0% 100.0% 不稳定 - - 0 HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 gpt-5.5 0/3 3/3 0.0% 100.0% 不稳定 - - 0 HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}

结果明细

#1 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1255 ms Tokens:113 时间:2026-08-31 06:20:08
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1321 ms Tokens:113 时间:2026-08-31 06:20:08
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:977 ms Tokens:113 时间:2026-08-31 06:20:09
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1233 ms Tokens:113 时间:2026-08-31 06:20:09
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1105 ms Tokens:113 时间:2026-08-31 06:20:10
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1540 ms Tokens:113 时间:2026-08-31 06:20:10
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1142 ms Tokens:113 时间:2026-08-31 06:20:11
JSON
{"status
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1100 ms Tokens:113 时间:2026-08-31 06:20:12
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1148 ms Tokens:113 时间:2026-08-31 06:20:12
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1140 ms Tokens:113 时间:2026-08-31 06:20:13
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1056 ms Tokens:113 时间:2026-08-31 06:20:14
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1243 ms Tokens:113 时间:2026-08-31 06:20:14
JSON
无输出内容。
#13 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:2983 ms Tokens:26 时间:2026-08-31 06:20:15
JSON
无输出内容。
#14 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:3126 ms Tokens:26 时间:2026-08-31 06:20:15
JSON
无输出内容。
#15 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:2440 ms Tokens:27 时间:2026-08-31 06:20:18
JSON
无输出内容。
#16 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5310 ms Tokens:26 时间:2026-08-31 06:20:18
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4475 ms Tokens:26 时间:2026-08-31 06:20:20
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue: Navigating the Nuances of Expert Communication**\n\nAlright, so the core of this request is for me to summarize a given text, but with a very specific constraint: it needs to be in the first person, as if these thoughts are *my* own. And not just a brief summary, but a \"fulsome\" one, detailing the *entire* thought process. The target audience is an \"expert in their field,\" which is a crucial cue. This means I don't need to over-explain basic concepts. Instead, I should lean into the intellectual engagement, the critical analysis, and the strategic decision-making that goes into formulating a response suitable for someone who already possesses a deep understanding of the subject matter.\n\nLet's break down what \"fulsome\" really means in this context. It's not just about length; it's about depth and thoroughness. It implies a comprehensive exploration of how I arrived at the final output. For an expert, this would involve:\n\n* **Deconstructing the Input:** First, I need to meticulously dissect the provided text. What are its main arguments? What is the author's under
#18 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3669 ms Tokens:202 时间:2026-08-31 06:20:24
JSON
{"status":"ok","message":"stable"}
#19 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4837 ms Tokens:26 时间:2026-08-31 06:20:24
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5983 ms Tokens:344 时间:2026-08-31 06:20:28
JSON
{"status":"ok","message":"stable"}
#21 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:531 ms Tokens:- 时间:2026-08-31 06:20:34
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#22 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:6455 ms Tokens:352 时间:2026-08-31 06:20:29
JSON
{"status":"ok","message":"stable"}
#23 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:522 ms Tokens:- 时间:2026-08-31 06:20:35
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:511 ms Tokens:- 时间:2026-08-31 06:20:35
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#25 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:727 ms Tokens:- 时间:2026-08-31 06:20:35
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#26 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:512 ms Tokens:- 时间:2026-08-31 06:20:36
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:515 ms Tokens:- 时间:2026-08-31 06:20:36
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2064 ms Tokens:115 时间:2026-08-31 06:20:36
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1799 ms Tokens:115 时间:2026-08-31 06:20:36
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2061 ms Tokens:115 时间:2026-08-31 06:20:38
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5647 ms Tokens:200 时间:2026-08-31 06:20:38
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7652 ms Tokens:240 时间:2026-08-31 06:20:40
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2159 ms Tokens:115 时间:2026-08-31 06:20:48
JSON
无输出内容。
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7012 ms Tokens:230 时间:2026-08-31 06:20:44
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:927 ms Tokens:153 时间:2026-08-31 06:20:51
JSON
无输出内容。
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2077 ms Tokens:115 时间:2026-08-31 06:20:50
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1524 ms Tokens:126 时间:2026-08-31 06:20:52
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1935 ms Tokens:125 时间:2026-08-31 06:20:52
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:216 ms Tokens:- 时间:2026-08-31 06:20:54
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#40 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:168 ms Tokens:- 时间:2026-08-31 06:20:54
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#41 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:178 ms Tokens:- 时间:2026-08-31 06:20:54
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1952 ms Tokens:135 时间:2026-08-31 06:20:53
JSON
{"status":"ok","message":"stable"}
#43 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:5158 ms Tokens:175 时间:2026-08-31 06:20:55
JSON
{"status":"ok","message":"stable"}
#44 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:4646 ms Tokens:184 时间:2026-08-31 06:20:55
JSON
{"status":"ok","message":"stable"}
#45 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:4179 ms Tokens:185 时间:2026-08-31 06:21:00
JSON
{"status":"ok","message":"stable"}

表格明细

渠道状态延迟 msHTTPTokens输出 / 错误
DeepSeek-v4-pro-01 成功 1255 200 113
DeepSeek-v4-pro-01 成功 1321 200 113
DeepSeek-v4-pro-03 成功 977 200 113
DeepSeek-v4-pro-01 成功 1233 200 113
DeepSeek-v4-pro-03 成功 1105 200 113
DeepSeek-v4-pro-03 成功 1540 200 113
DeepSeek-v4-pro-04 成功 1142 200 113 {"status
DeepSeek-v4-pro-04 成功 1100 200 113
DeepSeek-v4-pro-04 成功 1148 200 113
DeepSeek-v4-pro-02 成功 1140 200 113
DeepSeek-v4-pro-02 成功 1056 200 113
DeepSeek-v4-pro-02 成功 1243 200 113
jd-gemini-3.1-pro-preview 成功 2983 200 26
jd-gemini-3.1-pro-preview 成功 3126 200 26
jd-gemini-3.1-pro-preview 成功 2440 200 27
腾讯 Gemini 3.5 Flash 成功 5310 200 26 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I
腾讯 Gemini 3.5 Flash 成功 4475 200 26 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue: Navigating the Nuances of Expert Communication**\n\nAlright, so the core of this request is for me to summarize a given text, but with a very specific constraint: it needs to be in the first person, as if these thoughts are *my* own. And not just a brief summary, but a \"fulsome\" one, detailing the *entire* thought process. The target audience is an \"expert in their field,\" which is a crucial cue. This means I don't need to over-explain basic concepts. Instead, I should lean into the intellectual engagement, the critical analysis, and the strategic decision-making that goes into formulating a response suitable for someone who already possesses a deep understanding of the subject matter.\n\nLet's break down what \"fulsome\" really means in this context. It's not just about length; it's about depth and thoroughness. It implies a comprehensive exploration of how I arrived at the final output. For an expert, this would involve:\n\n* **Deconstructing the Input:** First, I need to meticulously dissect the provided text. What are its main arguments? What is the author's under
qwen3.6-plus 成功 3669 200 202 {"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash 成功 4837 200 26 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I
qwen3.6-plus 成功 5983 200 344 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 531 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 6455 200 352 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 522 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 511 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 727 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 512 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 515 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 2064 200 115
Kimi K3 - Aliyun Bailian 成功 1799 200 115
Kimi K3 - Aliyun Bailian 成功 2061 200 115
Kimi K3 成功 5647 200 200 {"status":"ok","message":"stable"}
Kimi K3 成功 7652 200 240 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2159 200 115
Kimi K3 成功 7012 200 230 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 927 200 153
Kimi K3 - TopenRouter 成功 2077 200 115
Qwen3.8-Max 成功 1524 200 126 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1935 200 125 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 216 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 168 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 178 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 1952 200 135 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5158 200 175 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4646 200 184 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4179 200 185 {"status":"ok","message":"stable"}