历史详情

Run ID: 20260829-235044-1f10747a

返回历史

测试结果

Run ID: 20260829-235044-1f10747a

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3552 ms
P95 / Tokens8154 / 4779
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 929 1129 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1084 1333 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1281 1437 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1354 1518 339
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1535 1717 345
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2136 2297 385
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2456 3147 554
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4541 7054 479
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5018 5803 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5617 6026 952
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 6593 8154 550
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 可用 10077 14226 80
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:786 ms Tokens:113 时间:2026-08-29 23:49:38
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:874 ms Tokens:113 时间:2026-08-29 23:49:38
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1129 ms Tokens:113 时间:2026-08-29 23:49:39
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1044 ms Tokens:113 时间:2026-08-29 23:49:39
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1500 ms Tokens:113 时间:2026-08-29 23:49:40
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1518 ms Tokens:113 时间:2026-08-29 23:49:40
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1325 ms Tokens:113 时间:2026-08-29 23:49:41
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1437 ms Tokens:113 时间:2026-08-29 23:49:41
JSON
无输出内容。
#9 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:767 ms Tokens:113 时间:2026-08-29 23:49:43
JSON
无输出内容。
#10 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1083 ms Tokens:113 时间:2026-08-29 23:49:43
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1333 ms Tokens:113 时间:2026-08-29 23:49:44
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1152 ms Tokens:113 时间:2026-08-29 23:49:44
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:13632 ms Tokens:27 时间:2026-08-29 23:49:45
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:14226 ms Tokens:27 时间:2026-08-29 23:49:45
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:2373 ms Tokens:26 时间:2026-08-29 23:49:59
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:4365 ms Tokens:26 时间:2026-08-29 23:49:59
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:5803 ms Tokens:26 时间:2026-08-29 23:50:01
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 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4887 ms Tokens:26 时间:2026-08-29 23:50:04
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
#19 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5190 ms Tokens:292 时间:2026-08-29 23:50:07
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5636 ms Tokens:324 时间:2026-08-29 23:50:08
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:634 ms Tokens:- 时间:2026-08-29 23:50:14
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:529 ms Tokens:- 时间:2026-08-29 23:50:15
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:527 ms Tokens:- 时间:2026-08-29 23:50:15
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:462 ms Tokens:- 时间:2026-08-29 23:50:16
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:464 ms Tokens:- 时间:2026-08-29 23:50:16
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:466 ms Tokens:- 时间:2026-08-29 23:50:17
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:6026 ms Tokens:336 时间:2026-08-29 23:50:12
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1619 ms Tokens:115 时间:2026-08-29 23:50:17
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1717 ms Tokens:115 时间:2026-08-29 23:50:18
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1269 ms Tokens:115 时间:2026-08-29 23:50:19
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5558 ms Tokens:169 时间:2026-08-29 23:50:20
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8154 ms Tokens:193 时间:2026-08-29 23:50:20
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2890 ms Tokens:198 时间:2026-08-29 23:50:28
JSON
{"status":"ok","message":"stable"}
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6069 ms Tokens:188 时间:2026-08-29 23:50:25
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1333 ms Tokens:153 时间:2026-08-29 23:50:31
JSON
无输出内容。
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:3147 ms Tokens:203 时间:2026-08-29 23:50:31
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1864 ms Tokens:125 时间:2026-08-29 23:50:33
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2247 ms Tokens:134 时间:2026-08-29 23:50:34
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:200 ms Tokens:- 时间:2026-08-29 23:50:36
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:2297 ms Tokens:126 时间:2026-08-29 23:50:35
JSON
{"status":"ok","message":"stable"}
#41 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:199 ms Tokens:- 时间:2026-08-29 23:50:37
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:238 ms Tokens:- 时间:2026-08-29 23:50:37
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:2807 ms Tokens:141 时间:2026-08-29 23:50:37
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:3762 ms Tokens:182 时间:2026-08-29 23:50:40
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:7054 ms Tokens:156 时间:2026-08-29 23:50:37
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 786 200 113
DeepSeek-v4-pro-01 成功 874 200 113
DeepSeek-v4-pro-01 成功 1129 200 113
DeepSeek-v4-pro-03 成功 1044 200 113
DeepSeek-v4-pro-03 成功 1500 200 113
DeepSeek-v4-pro-03 成功 1518 200 113
DeepSeek-v4-pro-04 成功 1325 200 113
DeepSeek-v4-pro-04 成功 1437 200 113
DeepSeek-v4-pro-02 成功 767 200 113
DeepSeek-v4-pro-04 成功 1083 200 113
DeepSeek-v4-pro-02 成功 1333 200 113
DeepSeek-v4-pro-02 成功 1152 200 113
jd-gemini-3.1-pro-preview 成功 13632 200 27
jd-gemini-3.1-pro-preview 成功 14226 200 27
jd-gemini-3.1-pro-preview 成功 2373 200 26
腾讯 Gemini 3.5 Flash 成功 4365 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 5803 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 4887 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 5190 200 292 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 5636 200 324 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 634 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 529 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 527 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 462 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 464 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 466 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 6026 200 336 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 1619 200 115
Kimi K3 - Aliyun Bailian 成功 1717 200 115
Kimi K3 - Aliyun Bailian 成功 1269 200 115
Kimi K3 成功 5558 200 169 {"status":"ok","message":"stable"}
Kimi K3 成功 8154 200 193 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2890 200 198 {"status":"ok","message":"stable"}
Kimi K3 成功 6069 200 188 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1333 200 153
Kimi K3 - TopenRouter 成功 3147 200 203 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1864 200 125 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2247 200 134 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 200 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2297 200 126 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 199 400 - 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
yulin-gemini-3.7-flash-high 成功 2807 200 141 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3762 200 182 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 7054 200 156 {"status":"ok","message":"stable"}