历史详情

Run ID: 20260831-052008-4dcb6c70

返回历史

测试结果

Run ID: 20260831-052008-4dcb6c70

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟2980 ms
P95 / Tokens6297 / 4866
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-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1021 1243 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1073 1136 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1089 1240 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1128 1207 339
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1362 1966 345
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1987 2058 389
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2110 2361 383
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4905 5935 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4915 5259 540
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 6278 7038 549
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 6825 10689 1174
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 2/3 1/3 66.67% 33.33% 不稳定 3113 3322 52 HTTP 400: {"error":{"message":"Signature is invalid: Signature format is invalid.","type":"invalid_request_error"}}
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:1011 ms Tokens:113 时间:2026-08-31 05:19:09
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1166 ms Tokens:113 时间:2026-08-31 05:19:09
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1207 ms Tokens:113 时间:2026-08-31 05:19:10
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1136 ms Tokens:113 时间:2026-08-31 05:19:10
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:977 ms Tokens:113 时间:2026-08-31 05:19:11
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1106 ms Tokens:113 时间:2026-08-31 05:19:11
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:894 ms Tokens:113 时间:2026-08-31 05:19:12
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1135 ms Tokens:113 时间:2026-08-31 05:19:12
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1240 ms Tokens:113 时间:2026-08-31 05:19:13
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1243 ms Tokens:113 时间:2026-08-31 05:19:13
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:732 ms Tokens:113 时间:2026-08-31 05:19:15
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1090 ms Tokens:113 时间:2026-08-31 05:19:14
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:3322 ms Tokens:26 时间:2026-08-31 05:19:15
JSON
无输出内容。
#14 jd-gemini-3.1-pro-preview 失败 HTTP 400
模型:gemini-3.1-pro-preview 延迟:5194 ms Tokens:- 时间:2026-08-31 05:19:15
JSON
HTTP 400: {"error":{"message":"Signature is invalid: Signature format is invalid.","type":"invalid_request_error"}}
#15 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:2904 ms Tokens:26 时间:2026-08-31 05:19:19
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:4439 ms Tokens:26 时间:2026-08-31 05:19:21
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:4343 ms Tokens:26 时间:2026-08-31 05:19:21
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:5935 ms Tokens:26 时间:2026-08-31 05:19:25
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:3813 ms Tokens:213 时间:2026-08-31 05:19:31
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:10689 ms Tokens:617 时间:2026-08-31 05:19:26
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:528 ms Tokens:- 时间:2026-08-31 05:19:37
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:536 ms Tokens:- 时间:2026-08-31 05:19:37
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:500 ms Tokens:- 时间:2026-08-31 05:19:38
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:465 ms Tokens:- 时间:2026-08-31 05:19:38
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:525 ms Tokens:- 时间:2026-08-31 05:19:39
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:467 ms Tokens:- 时间:2026-08-31 05:19:39
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:5973 ms Tokens:344 时间:2026-08-31 05:19:35
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1966 ms Tokens:115 时间:2026-08-31 05:19:40
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1150 ms Tokens:115 时间:2026-08-31 05:19:41
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:970 ms Tokens:115 时间:2026-08-31 05:19:41
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6297 ms Tokens:142 时间:2026-08-31 05:19:42
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7038 ms Tokens:225 时间:2026-08-31 05:19:42
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2361 ms Tokens:115 时间:2026-08-31 05:19:50
JSON
无输出内容。
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1779 ms Tokens:153 时间:2026-08-31 05:19:52
JSON
无输出内容。
#35 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5499 ms Tokens:182 时间:2026-08-31 05:19:48
JSON
{"status":"ok","message":"stable"}
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1886 ms Tokens:126 时间:2026-08-31 05:19:54
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2192 ms Tokens:115 时间:2026-08-31 05:19:54
JSON
{"
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2017 ms Tokens:135 时间:2026-08-31 05:19:56
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:191 ms Tokens:- 时间:2026-08-31 05:19:58
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#40 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2058 ms Tokens:128 时间:2026-08-31 05:19:56
JSON
{"status":"ok","message":"stable"}
#41 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:200 ms Tokens:- 时间:2026-08-31 05:19:58
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:171 ms Tokens:- 时间:2026-08-31 05:19:58
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#43 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:5175 ms Tokens:169 时间:2026-08-31 05:19:58
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:5259 ms Tokens:184 时间:2026-08-31 05:19:58
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:4312 ms Tokens:187 时间:2026-08-31 05:20:03
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 1011 200 113
DeepSeek-v4-pro-01 成功 1166 200 113
DeepSeek-v4-pro-01 成功 1207 200 113
DeepSeek-v4-pro-03 成功 1136 200 113
DeepSeek-v4-pro-03 成功 977 200 113
DeepSeek-v4-pro-03 成功 1106 200 113
DeepSeek-v4-pro-04 成功 894 200 113
DeepSeek-v4-pro-04 成功 1135 200 113
DeepSeek-v4-pro-04 成功 1240 200 113
DeepSeek-v4-pro-02 成功 1243 200 113
DeepSeek-v4-pro-02 成功 732 200 113
DeepSeek-v4-pro-02 成功 1090 200 113
jd-gemini-3.1-pro-preview 成功 3322 200 26
jd-gemini-3.1-pro-preview 失败 5194 400 - HTTP 400: {"error":{"message":"Signature is invalid: Signature format is invalid.","type":"invalid_request_error"}}
jd-gemini-3.1-pro-preview 成功 2904 200 26
腾讯 Gemini 3.5 Flash 成功 4439 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 4343 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 5935 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 3813 200 213 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 10689 200 617 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 528 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 536 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 500 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 465 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 525 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 467 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 5973 200 344 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 1966 200 115
Kimi K3 - Aliyun Bailian 成功 1150 200 115
Kimi K3 - Aliyun Bailian 成功 970 200 115
Kimi K3 成功 6297 200 142 {"status":"ok","message":"stable"}
Kimi K3 成功 7038 200 225 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2361 200 115
Kimi K3 - TopenRouter 成功 1779 200 153
Kimi K3 成功 5499 200 182 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1886 200 126 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2192 200 115 {"
Qwen3.8-Max 成功 2017 200 135 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 191 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2058 200 128 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 200 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 171 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 5175 200 169 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5259 200 184 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4312 200 187 {"status":"ok","message":"stable"}