历史详情

Run ID: 20260830-170754-4d7cfa2b

返回历史

测试结果

Run ID: 20260830-170754-4d7cfa2b

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3107 ms
P95 / Tokens6396 / 4949
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-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1053 1209 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1186 1250 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1214 1299 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1497 1608 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1728 2440 383
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1773 2022 390
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2145 2403 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 可用 4223 5638 317
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5048 6107 78
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5684 6786 600
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5841 10607 1008
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5894 6396 472
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:886 ms Tokens:113 时间:2026-08-30 17:06:54
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1065 ms Tokens:113 时间:2026-08-30 17:06:54
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1209 ms Tokens:113 时间:2026-08-30 17:06:55
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1120 ms Tokens:113 时间:2026-08-30 17:06:55
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1189 ms Tokens:113 时间:2026-08-30 17:06:56
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1250 ms Tokens:113 时间:2026-08-30 17:06:56
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1346 ms Tokens:113 时间:2026-08-30 17:06:57
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1608 ms Tokens:113 时间:2026-08-30 17:06:57
JSON
无输出内容。
#9 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1299 ms Tokens:113 时间:2026-08-30 17:06:59
JSON
无输出内容。
#10 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1538 ms Tokens:113 时间:2026-08-30 17:06:59
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1126 ms Tokens:113 时间:2026-08-30 17:07:00
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1217 ms Tokens:113 时间:2026-08-30 17:07:00
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:4316 ms Tokens:264 时间:2026-08-30 17:07:01
JSON
{"status":"ok","message":"stable"}
#14 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:5638 ms Tokens:26 时间:2026-08-30 17:07:01
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:2716 ms Tokens:27 时间:2026-08-30 17:07:05
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:4546 ms Tokens:26 时间:2026-08-30 17:07:08
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:6107 ms Tokens:26 时间:2026-08-30 17:07:07
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
#18 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3380 ms Tokens:189 时间:2026-08-30 17:07:13
JSON
{"status":"ok","message":"stable"}
#19 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4493 ms Tokens:26 时间:2026-08-30 17:07:13
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:3537 ms Tokens:202 时间:2026-08-30 17:07:17
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:537 ms Tokens:- 时间:2026-08-30 17:07:21
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:524 ms Tokens:- 时间:2026-08-30 17:07:21
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:530 ms Tokens:- 时间:2026-08-30 17:07:22
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:532 ms Tokens:- 时间:2026-08-30 17:07:22
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:434 ms Tokens:- 时间:2026-08-30 17:07:23
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:516 ms Tokens:- 时间:2026-08-30 17:07:23
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1911 ms Tokens:115 时间:2026-08-30 17:07:24
JSON
无输出内容。
#28 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:10607 ms Tokens:617 时间:2026-08-30 17:07:17
JSON
{"status":"ok","message":"stable"}
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2123 ms Tokens:115 时间:2026-08-30 17:07:26
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2403 ms Tokens:115 时间:2026-08-30 17:07:27
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6786 ms Tokens:233 时间:2026-08-30 17:07:28
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5744 ms Tokens:194 时间:2026-08-30 17:07:30
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2440 ms Tokens:115 时间:2026-08-30 17:07:35
JSON
{"status
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:4522 ms Tokens:173 时间:2026-08-30 17:07:35
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1996 ms Tokens:115 时间:2026-08-30 17:07:38
JSON
{"status":"ok","message
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:750 ms Tokens:153 时间:2026-08-30 17:07:39
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1610 ms Tokens:125 时间:2026-08-30 17:07:40
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2022 ms Tokens:137 时间:2026-08-30 17:07:40
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:246 ms Tokens:- 时间:2026-08-30 17:07:42
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:207 ms Tokens:- 时间:2026-08-30 17:07:42
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:238 ms Tokens:- 时间:2026-08-30 17:07:42
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:1689 ms Tokens:128 时间:2026-08-30 17:07:41
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:5175 ms Tokens:158 时间:2026-08-30 17:07:43
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:6396 ms Tokens:164 时间:2026-08-30 17:07:43
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:6112 ms Tokens:150 时间:2026-08-30 17:07:48
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 886 200 113
DeepSeek-v4-pro-01 成功 1065 200 113
DeepSeek-v4-pro-01 成功 1209 200 113
DeepSeek-v4-pro-03 成功 1120 200 113
DeepSeek-v4-pro-03 成功 1189 200 113
DeepSeek-v4-pro-03 成功 1250 200 113
DeepSeek-v4-pro-04 成功 1346 200 113
DeepSeek-v4-pro-04 成功 1608 200 113
DeepSeek-v4-pro-02 成功 1299 200 113
DeepSeek-v4-pro-04 成功 1538 200 113
DeepSeek-v4-pro-02 成功 1126 200 113
DeepSeek-v4-pro-02 成功 1217 200 113
jd-gemini-3.1-pro-preview 成功 4316 200 264 {"status":"ok","message":"stable"}
jd-gemini-3.1-pro-preview 成功 5638 200 26
jd-gemini-3.1-pro-preview 成功 2716 200 27
腾讯 Gemini 3.5 Flash 成功 4546 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 6107 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 3380 200 189 {"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash 成功 4493 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 3537 200 202 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 537 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 524 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 530 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 532 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 434 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 516 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 1911 200 115
qwen3.6-plus 成功 10607 200 617 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 2123 200 115
Kimi K3 - Aliyun Bailian 成功 2403 200 115
Kimi K3 成功 6786 200 233 {"status":"ok","message":"stable"}
Kimi K3 成功 5744 200 194 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2440 200 115 {"status
Kimi K3 成功 4522 200 173 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1996 200 115 {"status":"ok","message
Kimi K3 - TopenRouter 成功 750 200 153
Qwen3.8-Max 成功 1610 200 125 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2022 200 137 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 246 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 207 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 238 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 1689 200 128 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5175 200 158 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 6396 200 164 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 6112 200 150 {"status":"ok","message":"stable"}