历史详情

Run ID: 20260830-130358-e54747c7

返回历史

测试结果

Run ID: 20260830-130358-e54747c7

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3514 ms
P95 / Tokens7315 / 5083
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 1044 1241 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1148 1217 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1154 1207 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1250 1431 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1785 1955 391
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2438 2612 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 4095 4913 304
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5020 5549 498
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5186 5740 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5562 7182 929
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 6152 10335 595
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 7339 8536 587
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:1086 ms Tokens:113 时间:2026-08-30 13:02:52
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1217 ms Tokens:113 时间:2026-08-30 13:02:52
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1142 ms Tokens:113 时间:2026-08-30 13:02:53
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1431 ms Tokens:113 时间:2026-08-30 13:02:53
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1315 ms Tokens:113 时间:2026-08-30 13:02:54
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1006 ms Tokens:113 时间:2026-08-30 13:02:55
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1207 ms Tokens:113 时间:2026-08-30 13:02:56
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1200 ms Tokens:113 时间:2026-08-30 13:02:56
JSON
无输出内容。
#9 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:796 ms Tokens:113 时间:2026-08-30 13:02:57
JSON
无输出内容。
#10 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1056 ms Tokens:113 时间:2026-08-30 13:02:57
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1095 ms Tokens:113 时间:2026-08-30 13:02:58
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1241 ms Tokens:113 时间:2026-08-30 13:02:58
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:2982 ms Tokens:26 时间:2026-08-30 13:02:59
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:4913 ms Tokens:26 时间:2026-08-30 13:02:59
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:4391 ms Tokens:252 时间:2026-08-30 13:03:02
JSON
{"status":"ok","message":"stable"}
#16 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4603 ms Tokens:26 时间:2026-08-30 13:03:04
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5740 ms Tokens:26 时间:2026-08-30 13:03:06
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
#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5217 ms Tokens:26 时间:2026-08-30 13:03:08
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
#19 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4226 ms Tokens:239 时间:2026-08-30 13:03:12
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5279 ms Tokens:291 时间:2026-08-30 13:03:13
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:538 ms Tokens:- 时间:2026-08-30 13:03:19
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 13:03:19
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:503 ms Tokens:- 时间:2026-08-30 13:03:20
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:459 ms Tokens:- 时间:2026-08-30 13:03:20
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:494 ms Tokens:- 时间:2026-08-30 13:03:21
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:478 ms Tokens:- 时间:2026-08-30 13:03:21
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:7182 ms Tokens:399 时间:2026-08-30 13:03:16
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2544 ms Tokens:115 时间:2026-08-30 13:03:22
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2612 ms Tokens:115 时间:2026-08-30 13:03:24
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2159 ms Tokens:115 时间:2026-08-30 13:03:24
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6166 ms Tokens:194 时间:2026-08-30 13:03:26
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7315 ms Tokens:175 时间:2026-08-30 13:03:26
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:6537 ms Tokens:187 时间:2026-08-30 13:03:34
JSON
{"status":"ok","message":"stable"}
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8536 ms Tokens:218 时间:2026-08-30 13:03:32
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1586 ms Tokens:153 时间:2026-08-30 13:03:40
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1705 ms Tokens:136 时间:2026-08-30 13:03:42
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1955 ms Tokens:128 时间:2026-08-30 13:03:44
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1697 ms Tokens:127 时间:2026-08-30 13:03:46
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:174 ms Tokens:- 时间:2026-08-30 13:03:47
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:214 ms Tokens:- 时间:2026-08-30 13:03:47
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:195 ms Tokens:- 时间:2026-08-30 13:03:48
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:10335 ms Tokens:255 时间:2026-08-30 13:03:41
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:4897 ms Tokens:175 时间:2026-08-30 13:03:48
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:4614 ms Tokens:166 时间:2026-08-30 13:03:51
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:5549 ms Tokens:157 时间:2026-08-30 13:03:53
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 1086 200 113
DeepSeek-v4-pro-01 成功 1217 200 113
DeepSeek-v4-pro-01 成功 1142 200 113
DeepSeek-v4-pro-03 成功 1431 200 113
DeepSeek-v4-pro-03 成功 1315 200 113
DeepSeek-v4-pro-03 成功 1006 200 113
DeepSeek-v4-pro-04 成功 1207 200 113
DeepSeek-v4-pro-04 成功 1200 200 113
DeepSeek-v4-pro-02 成功 796 200 113
DeepSeek-v4-pro-04 成功 1056 200 113
DeepSeek-v4-pro-02 成功 1095 200 113
DeepSeek-v4-pro-02 成功 1241 200 113
jd-gemini-3.1-pro-preview 成功 2982 200 26
jd-gemini-3.1-pro-preview 成功 4913 200 26
jd-gemini-3.1-pro-preview 成功 4391 200 252 {"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash 成功 4603 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 5740 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 5217 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 4226 200 239 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 5279 200 291 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 538 403 - 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 503 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 459 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 494 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 478 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 7182 200 399 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 2544 200 115
Kimi K3 - Aliyun Bailian 成功 2612 200 115
Kimi K3 - Aliyun Bailian 成功 2159 200 115
Kimi K3 成功 6166 200 194 {"status":"ok","message":"stable"}
Kimi K3 成功 7315 200 175 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 6537 200 187 {"status":"ok","message":"stable"}
Kimi K3 成功 8536 200 218 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1586 200 153
Qwen3.8-Max 成功 1705 200 136 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1955 200 128 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1697 200 127 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 174 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 214 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 195 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Kimi K3 - TopenRouter 成功 10335 200 255 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4897 200 175 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4614 200 166 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5549 200 157 {"status":"ok","message":"stable"}