历史详情

Run ID: 20260828-171743-24902631

返回历史

测试结果

Run ID: 20260828-171743-24902631

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3612 ms
P95 / Tokens8856 / 4489
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 886 1093 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 905 1245 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1018 1400 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1388 1445 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2016 2327 384
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2712 3239 78
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 可用 3250 5396 345
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 稳定 3457 3855 476
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 稳定 4764 4886 804
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4948 5371 78
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 7850 8856 544
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 10153 14588 424
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:1287 ms Tokens:113 时间:2026-08-28 17:16:35
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1445 ms Tokens:113 时间:2026-08-28 17:16:35
JSON
{"status":"ok","message
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:662 ms Tokens:113 时间:2026-08-28 17:16:37
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1434 ms Tokens:113 时间:2026-08-28 17:16:36
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:992 ms Tokens:113 时间:2026-08-28 17:16:37
JSON
无输出内容。
#6 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:752 ms Tokens:113 时间:2026-08-28 17:16:38
JSON
无输出内容。
#7 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1400 ms Tokens:113 时间:2026-08-28 17:16:38
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:813 ms Tokens:113 时间:2026-08-28 17:16:39
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1093 ms Tokens:113 时间:2026-08-28 17:16:39
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:726 ms Tokens:113 时间:2026-08-28 17:16:40
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:744 ms Tokens:113 时间:2026-08-28 17:16:40
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1245 ms Tokens:113 时间:2026-08-28 17:16:41
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:3239 ms Tokens:26 时间:2026-08-28 17:16:41
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:2584 ms Tokens:26 时间:2026-08-28 17:16:42
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:2313 ms Tokens:26 时间:2026-08-28 17:16:44
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:4636 ms Tokens:26 时间:2026-08-28 17:16:44
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4839 ms Tokens:26 时间:2026-08-28 17:16:47
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 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5371 ms Tokens:26 时间:2026-08-28 17:16:49
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
#19 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4698 ms Tokens:268 时间:2026-08-28 17:16:52
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4886 ms Tokens:268 时间:2026-08-28 17:16:54
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:535 ms Tokens:- 时间:2026-08-28 17:16:59
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#22 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:534 ms Tokens:- 时间:2026-08-28 17:17:00
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#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:2026-08-28 17:17:00
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4709 ms Tokens:268 时间:2026-08-28 17:16:56
JSON
{"status":"ok","message":"stable"}
#25 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:656 ms Tokens:- 时间:2026-08-28 17:17:01
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:608 ms Tokens:- 时间:2026-08-28 17:17:01
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:570 ms Tokens:- 时间:2026-08-28 17:17:02
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:3062 ms Tokens:115 时间:2026-08-28 17:17:02
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1292 ms Tokens:115 时间:2026-08-28 17:17:05
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:5396 ms Tokens:115 时间:2026-08-28 17:17:02
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8856 ms Tokens:196 时间:2026-08-28 17:17:06
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8598 ms Tokens:233 时间:2026-08-28 17:17:07
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1454 ms Tokens:115 时间:2026-08-28 17:17:16
JSON
无输出内容。
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6097 ms Tokens:115 时间:2026-08-28 17:17:15
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:14419 ms Tokens:145 时间:2026-08-28 17:17:17
JSON
{"status":"ok","message":"stable"}
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1710 ms Tokens:128 时间:2026-08-28 17:17:31
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2011 ms Tokens:130 时间:2026-08-28 17:17:33
JSON
{"status":"ok","message":"stable"}
#38 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:14588 ms Tokens:164 时间:2026-08-28 17:17:21
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:202 ms Tokens:- 时间:2026-08-28 17:17:36
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:264 ms Tokens:- 时间:2026-08-28 17:17:36
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:196 ms Tokens:- 时间:2026-08-28 17:17:36
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:2327 ms Tokens:126 时间:2026-08-28 17:17:35
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:3265 ms Tokens:166 时间:2026-08-28 17:17:37
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:3855 ms Tokens:152 时间:2026-08-28 17:17:37
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:3253 ms Tokens:158 时间:2026-08-28 17:17:40
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 1287 200 113
DeepSeek-v4-pro-01 成功 1445 200 113 {"status":"ok","message
DeepSeek-v4-pro-03 成功 662 200 113
DeepSeek-v4-pro-01 成功 1434 200 113
DeepSeek-v4-pro-03 成功 992 200 113
DeepSeek-v4-pro-04 成功 752 200 113
DeepSeek-v4-pro-03 成功 1400 200 113
DeepSeek-v4-pro-04 成功 813 200 113
DeepSeek-v4-pro-04 成功 1093 200 113
DeepSeek-v4-pro-02 成功 726 200 113
DeepSeek-v4-pro-02 成功 744 200 113
DeepSeek-v4-pro-02 成功 1245 200 113
jd-gemini-3.1-pro-preview 成功 3239 200 26
jd-gemini-3.1-pro-preview 成功 2584 200 26
jd-gemini-3.1-pro-preview 成功 2313 200 26
腾讯 Gemini 3.5 Flash 成功 4636 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
腾讯 Gemini 3.5 Flash 成功 4839 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
腾讯 Gemini 3.5 Flash 成功 5371 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 4698 200 268 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 4886 200 268 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 535 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 534 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 522 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 4709 200 268 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 656 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 608 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 570 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 3062 200 115
Kimi K3 - Aliyun Bailian 成功 1292 200 115
Kimi K3 - Aliyun Bailian 成功 5396 200 115
Kimi K3 成功 8856 200 196 {"status":"ok","message":"stable"}
Kimi K3 成功 8598 200 233 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1454 200 115
Kimi K3 成功 6097 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 14419 200 145 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1710 200 128 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2011 200 130 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 14588 200 164 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 202 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 264 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 196 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2327 200 126 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3265 200 166 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3855 200 152 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3253 200 158 {"status":"ok","message":"stable"}