历史详情

Run ID: 20260830-150556-c3e297c2

返回历史

测试结果

Run ID: 20260830-150556-c3e297c2

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3090 ms
P95 / Tokens7226 / 4565
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-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1124 1332 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1194 1269 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1355 1470 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1711 2368 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1875 2421 397
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1989 2221 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2548 2667 78
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2571 2573 345
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4911 5826 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5084 7226 814
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5554 6668 535
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 7164 8437 617
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:1113 ms Tokens:113 时间:2026-08-30 15:04:55
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1269 ms Tokens:113 时间:2026-08-30 15:04:55
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1202 ms Tokens:113 时间:2026-08-30 15:04:56
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1332 ms Tokens:113 时间:2026-08-30 15:04:56
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:900 ms Tokens:113 时间:2026-08-30 15:04:58
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1140 ms Tokens:113 时间:2026-08-30 15:04:58
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1441 ms Tokens:113 时间:2026-08-30 15:04:58
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1155 ms Tokens:113 时间:2026-08-30 15:04:59
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1470 ms Tokens:113 时间:2026-08-30 15:05:00
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1566 ms Tokens:113 时间:2026-08-30 15:05:00
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1200 ms Tokens:113 时间:2026-08-30 15:05:02
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:2368 ms Tokens:113 时间:2026-08-30 15:05:01
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:2395 ms Tokens:26 时间:2026-08-30 15:05:03
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:2667 ms Tokens:26 时间:2026-08-30 15:05:04
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:2583 ms Tokens:26 时间:2026-08-30 15:05:05
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:5826 ms Tokens:26 时间:2026-08-30 15:05:06
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:4589 ms Tokens:26 时间:2026-08-30 15:05:08
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:4030 ms Tokens:214 时间:2026-08-30 15:05:12
JSON
{"status":"ok","message":"stable"}
#19 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4318 ms Tokens:26 时间:2026-08-30 15:05:12
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
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3996 ms Tokens:214 时间:2026-08-30 15:05:17
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:523 ms Tokens:- 时间:2026-08-30 15:05:21
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:549 ms Tokens:- 时间:2026-08-30 15:05:21
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:535 ms Tokens:- 时间:2026-08-30 15:05:22
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:503 ms Tokens:- 时间:2026-08-30 15:05:22
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:483 ms Tokens:- 时间:2026-08-30 15:05:23
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:547 ms Tokens:- 时间:2026-08-30 15:05:23
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:7226 ms Tokens:386 时间:2026-08-30 15:05:16
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1884 ms Tokens:115 时间:2026-08-30 15:05:24
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1863 ms Tokens:115 时间:2026-08-30 15:05:24
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2221 ms Tokens:115 时间:2026-08-30 15:05:26
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8341 ms Tokens:218 时间:2026-08-30 15:05:26
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8437 ms Tokens:207 时间:2026-08-30 15:05:28
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:4716 ms Tokens:192 时间:2026-08-30 15:05:34
JSON
{"status":"ok","message":"stable"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2572 ms Tokens:115 时间:2026-08-30 15:05:36
JSON
{"status
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2569 ms Tokens:115 时间:2026-08-30 15:05:39
JSON
无输出内容。
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2573 ms Tokens:115 时间:2026-08-30 15:05:39
JSON
{"
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1429 ms Tokens:117 时间:2026-08-30 15:05:41
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1776 ms Tokens:134 时间:2026-08-30 15:05:41
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:233 ms Tokens:- 时间:2026-08-30 15:05:43
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:156 ms Tokens:- 时间:2026-08-30 15:05:43
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:180 ms Tokens:- 时间:2026-08-30 15:05:44
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:2421 ms Tokens:146 时间:2026-08-30 15:05:43
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:5174 ms Tokens:176 时间:2026-08-30 15:05:44
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:4820 ms Tokens:167 时间:2026-08-30 15:05:45
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:6668 ms Tokens:192 时间:2026-08-30 15:05:49
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 1113 200 113
DeepSeek-v4-pro-01 成功 1269 200 113
DeepSeek-v4-pro-01 成功 1202 200 113
DeepSeek-v4-pro-03 成功 1332 200 113
DeepSeek-v4-pro-03 成功 900 200 113
DeepSeek-v4-pro-03 成功 1140 200 113
DeepSeek-v4-pro-04 成功 1441 200 113
DeepSeek-v4-pro-04 成功 1155 200 113
DeepSeek-v4-pro-04 成功 1470 200 113
DeepSeek-v4-pro-02 成功 1566 200 113
DeepSeek-v4-pro-02 成功 1200 200 113
DeepSeek-v4-pro-02 成功 2368 200 113
jd-gemini-3.1-pro-preview 成功 2395 200 26
jd-gemini-3.1-pro-preview 成功 2667 200 26
jd-gemini-3.1-pro-preview 成功 2583 200 26
腾讯 Gemini 3.5 Flash 成功 5826 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 4589 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 4030 200 214 {"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash 成功 4318 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 3996 200 214 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 523 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 549 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 535 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 503 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 483 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 547 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 7226 200 386 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 1884 200 115
Kimi K3 - Aliyun Bailian 成功 1863 200 115
Kimi K3 - Aliyun Bailian 成功 2221 200 115
Kimi K3 成功 8341 200 218 {"status":"ok","message":"stable"}
Kimi K3 成功 8437 200 207 {"status":"ok","message":"stable"}
Kimi K3 成功 4716 200 192 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2572 200 115 {"status
Kimi K3 - TopenRouter 成功 2569 200 115
Kimi K3 - TopenRouter 成功 2573 200 115 {"
Qwen3.8-Max 成功 1429 200 117 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1776 200 134 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 233 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 156 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 180 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2421 200 146 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5174 200 176 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4820 200 167 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 6668 200 192 {"status":"ok","message":"stable"}