历史详情

Run ID: 20260829-033011-6d5bc915

返回历史

测试结果

Run ID: 20260829-033011-6d5bc915

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟4011 ms
P95 / Tokens8539 / 4868
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 1261 1333 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1322 2001 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1332 1392 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1740 2301 345
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1952 2162 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2152 2864 387
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4770 5433 552
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4934 5084 78
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 可用 5688 8539 345
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5741 6683 511
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 7058 8580 1216
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 可用 10184 26440 78
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:2138 ms Tokens:113 时间:2026-08-29 03:28:54
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:2162 ms Tokens:113 时间:2026-08-29 03:28:54
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1306 ms Tokens:113 时间:2026-08-29 03:28:57
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1558 ms Tokens:113 时间:2026-08-29 03:28:57
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1333 ms Tokens:113 时间:2026-08-29 03:28:58
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1146 ms Tokens:113 时间:2026-08-29 03:28:58
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:833 ms Tokens:113 时间:2026-08-29 03:28:59
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1133 ms Tokens:113 时间:2026-08-29 03:28:59
JSON
无输出内容。
#9 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1375 ms Tokens:113 时间:2026-08-29 03:29:00
JSON
无输出内容。
#10 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:2001 ms Tokens:113 时间:2026-08-29 03:29:00
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1230 ms Tokens:113 时间:2026-08-29 03:29:02
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1392 ms Tokens:113 时间:2026-08-29 03:29:02
JSON
{"status
#13 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:2036 ms Tokens:26 时间:2026-08-29 03:29:03
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:2076 ms Tokens:26 时间:2026-08-29 03:29:06
JSON
无输出内容。
#15 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5022 ms Tokens:26 时间:2026-08-29 03:29:08
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
#16 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5084 ms Tokens:26 时间:2026-08-29 03:29:13
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:4696 ms Tokens:26 时间:2026-08-29 03:29:18
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:4354 ms Tokens:251 时间:2026-08-29 03:29:22
JSON
{"status":"ok","message":"stable"}
#19 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:26440 ms Tokens:26 时间:2026-08-29 03:29:03
JSON
无输出内容。
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:8240 ms Tokens:466 时间:2026-08-29 03:29:27
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:542 ms Tokens:- 时间:2026-08-29 03:29:35
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:544 ms Tokens:- 时间:2026-08-29 03:29:36
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:444 ms Tokens:- 时间:2026-08-29 03:29:36
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:488 ms Tokens:- 时间:2026-08-29 03:29:37
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:531 ms Tokens:- 时间:2026-08-29 03:29:37
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#26 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:8580 ms Tokens:499 时间:2026-08-29 03:29:29
JSON
{"status":"ok","message":"stable"}
#27 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:482 ms Tokens:- 时间:2026-08-29 03:29:38
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:5924 ms Tokens:115 时间:2026-08-29 03:29:38
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:8539 ms Tokens:115 时间:2026-08-29 03:29:38
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2601 ms Tokens:115 时间:2026-08-29 03:29:44
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6071 ms Tokens:179 时间:2026-08-29 03:29:47
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6683 ms Tokens:217 时间:2026-08-29 03:29:47
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1631 ms Tokens:115 时间:2026-08-29 03:29:53
JSON
{"
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1289 ms Tokens:115 时间:2026-08-29 03:29:55
JSON
{"
#35 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:4469 ms Tokens:115 时间:2026-08-29 03:29:53
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2301 ms Tokens:115 时间:2026-08-29 03:29:56
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1758 ms Tokens:125 时间:2026-08-29 03:29:57
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1836 ms Tokens:127 时间:2026-08-29 03:29:58
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:217 ms Tokens:- 时间:2026-08-29 03:30:00
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:174 ms Tokens:- 时间:2026-08-29 03:30:01
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:2026-08-29 03:30:01
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:2864 ms Tokens:135 时间:2026-08-29 03:29:59
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:4573 ms Tokens:199 时间:2026-08-29 03:30:02
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:5433 ms Tokens:192 时间:2026-08-29 03:30:01
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:4305 ms Tokens:161 时间:2026-08-29 03:30:06
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 2138 200 113
DeepSeek-v4-pro-01 成功 2162 200 113
DeepSeek-v4-pro-03 成功 1306 200 113
DeepSeek-v4-pro-01 成功 1558 200 113
DeepSeek-v4-pro-03 成功 1333 200 113
DeepSeek-v4-pro-03 成功 1146 200 113
DeepSeek-v4-pro-04 成功 833 200 113
DeepSeek-v4-pro-04 成功 1133 200 113
DeepSeek-v4-pro-02 成功 1375 200 113
DeepSeek-v4-pro-04 成功 2001 200 113
DeepSeek-v4-pro-02 成功 1230 200 113
DeepSeek-v4-pro-02 成功 1392 200 113 {"status
jd-gemini-3.1-pro-preview 成功 2036 200 26
jd-gemini-3.1-pro-preview 成功 2076 200 26
腾讯 Gemini 3.5 Flash 成功 5022 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 5084 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 4696 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 4354 200 251 {"status":"ok","message":"stable"}
jd-gemini-3.1-pro-preview 成功 26440 200 26
qwen3.6-plus 成功 8240 200 466 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 542 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 544 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 444 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 488 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 531 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 8580 200 499 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 482 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 5924 200 115
Kimi K3 - Aliyun Bailian 成功 8539 200 115
Kimi K3 - Aliyun Bailian 成功 2601 200 115
Kimi K3 成功 6071 200 179 {"status":"ok","message":"stable"}
Kimi K3 成功 6683 200 217 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1631 200 115 {"
Kimi K3 - TopenRouter 成功 1289 200 115 {"
Kimi K3 成功 4469 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 2301 200 115
Qwen3.8-Max 成功 1758 200 125 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1836 200 127 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 217 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 174 400 - 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 2864 200 135 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4573 200 199 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5433 200 192 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4305 200 161 {"status":"ok","message":"stable"}