历史详情

Run ID: 20260827-083157-6d2887ed

返回历史

测试结果

Run ID: 20260827-083157-6d2887ed

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3673 ms
P95 / Tokens7575 / 4724
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 830 1117 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 887 1099 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1192 1370 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1235 1307 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2137 2339 393
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 稳定 2155 2489 495
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2322 2634 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2362 2712 78
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 4256 4469 348
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5777 7228 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 6994 7575 1199
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 13930 21726 432
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:676 ms Tokens:113 时间:2026-08-27 08:30:49
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:697 ms Tokens:113 时间:2026-08-27 08:30:49
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1117 ms Tokens:113 时间:2026-08-27 08:30:50
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1370 ms Tokens:113 时间:2026-08-27 08:30:50
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1021 ms Tokens:113 时间:2026-08-27 08:30:51
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1186 ms Tokens:113 时间:2026-08-27 08:30:51
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1099 ms Tokens:113 时间:2026-08-27 08:30:52
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:748 ms Tokens:113 时间:2026-08-27 08:30:52
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:815 ms Tokens:113 时间:2026-08-27 08:30:53
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1198 ms Tokens:113 时间:2026-08-27 08:30:53
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1200 ms Tokens:113 时间:2026-08-27 08:30:54
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1307 ms Tokens:113 时间:2026-08-27 08:30:54
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:2712 ms Tokens:26 时间:2026-08-27 08:30:55
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:2156 ms Tokens:26 时间:2026-08-27 08:30:55
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:2218 ms Tokens:26 时间:2026-08-27 08:30:58
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:7228 ms Tokens:26 时间:2026-08-27 08:30:58
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:5893 ms Tokens:26 时间:2026-08-27 08:31:00
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:4211 ms Tokens:26 时间:2026-08-27 08:31:05
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:5945 ms Tokens:331 时间:2026-08-27 08:31:06
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:7575 ms Tokens:434 时间:2026-08-27 08:31:09
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:509 ms Tokens:- 时间:2026-08-27 08:31:17
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:516 ms Tokens:- 时间:2026-08-27 08:31:17
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:545 ms Tokens:- 时间:2026-08-27 08:31:18
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:456 ms Tokens:- 时间:2026-08-27 08:31:18
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#25 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:7464 ms Tokens:434 时间:2026-08-27 08:31:12
JSON
{"status":"ok","message":"stable"}
#26 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:477 ms Tokens:- 时间:2026-08-27 08:31:19
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:522 ms Tokens:- 时间:2026-08-27 08:31:19
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:1940 ms Tokens:115 时间:2026-08-27 08:31:19
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2392 ms Tokens:115 时间:2026-08-27 08:31:20
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2634 ms Tokens:115 时间:2026-08-27 08:31:21
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:14128 ms Tokens:202 时间:2026-08-27 08:31:24
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:21726 ms Tokens:115 时间:2026-08-27 08:31:22
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"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5938 ms Tokens:115 时间:2026-08-27 08:31:38
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:3832 ms Tokens:116 时间:2026-08-27 08:31:44
JSON
无输出内容。
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:4469 ms Tokens:116 时间:2026-08-27 08:31:44
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2093 ms Tokens:134 时间:2026-08-27 08:31:48
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:4467 ms Tokens:116 时间:2026-08-27 08:31:48
JSON
无输出内容。
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1980 ms Tokens:130 时间:2026-08-27 08:31:50
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:172 ms Tokens:- 时间:2026-08-27 08:31:52
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:200 ms Tokens:- 时间:2026-08-27 08:31:52
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:174 ms Tokens:- 时间:2026-08-27 08:31:53
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:2339 ms Tokens:129 时间:2026-08-27 08:31:52
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:2489 ms Tokens:174 时间:2026-08-27 08:31:53
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:2182 ms Tokens:158 时间:2026-08-27 08:31:54
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:1796 ms Tokens:163 时间:2026-08-27 08:31:55
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 676 200 113
DeepSeek-v4-pro-01 成功 697 200 113
DeepSeek-v4-pro-01 成功 1117 200 113
DeepSeek-v4-pro-03 成功 1370 200 113
DeepSeek-v4-pro-03 成功 1021 200 113
DeepSeek-v4-pro-03 成功 1186 200 113
DeepSeek-v4-pro-04 成功 1099 200 113
DeepSeek-v4-pro-04 成功 748 200 113
DeepSeek-v4-pro-04 成功 815 200 113
DeepSeek-v4-pro-02 成功 1198 200 113
DeepSeek-v4-pro-02 成功 1200 200 113
DeepSeek-v4-pro-02 成功 1307 200 113
jd-gemini-3.1-pro-preview 成功 2712 200 26
jd-gemini-3.1-pro-preview 成功 2156 200 26
jd-gemini-3.1-pro-preview 成功 2218 200 26
腾讯 Gemini 3.5 Flash 成功 7228 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 5893 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 4211 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 5945 200 331 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 7575 200 434 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 509 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 516 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 545 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 456 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 7464 200 434 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 477 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 522 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 1940 200 115
Kimi K3 - Aliyun Bailian 成功 2392 200 115
Kimi K3 - Aliyun Bailian 成功 2634 200 115
Kimi K3 成功 14128 200 202 {"status":"ok","message":"stable"}
Kimi K3 成功 21726 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 成功 5938 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 3832 200 116
Kimi K3 - TopenRouter 成功 4469 200 116
Qwen3.8-Max 成功 2093 200 134 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 4467 200 116
Qwen3.8-Max 成功 1980 200 130 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 172 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 200 400 - 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
Qwen3.8-Max 成功 2339 200 129 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2489 200 174 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2182 200 158 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 1796 200 163 {"status":"ok","message":"stable"}