历史详情

Run ID: 20260830-075854-69b3bf7c

返回历史

测试结果

Run ID: 20260830-075854-69b3bf7c

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3597 ms
P95 / Tokens7595 / 4634
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-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 901 1018 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 923 1066 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 960 1067 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1011 1130 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1467 1547 459
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2009 2080 387
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2404 3168 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 可用 4273 7595 79
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 4809 6977 786
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4859 5796 78
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 8181 10925 664
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 11372 25947 480
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:1077 ms Tokens:113 时间:2026-08-30 07:57:39
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1130 ms Tokens:113 时间:2026-08-30 07:57:39
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:663 ms Tokens:113 时间:2026-08-30 07:57:41
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:826 ms Tokens:113 时间:2026-08-30 07:57:40
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1066 ms Tokens:113 时间:2026-08-30 07:57:41
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1040 ms Tokens:113 时间:2026-08-30 07:57:41
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:742 ms Tokens:113 时间:2026-08-30 07:57:42
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:943 ms Tokens:113 时间:2026-08-30 07:57:42
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1018 ms Tokens:113 时间:2026-08-30 07:57:43
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1067 ms Tokens:113 时间:2026-08-30 07:57:43
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:782 ms Tokens:113 时间:2026-08-30 07:57:44
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1033 ms Tokens:113 时间:2026-08-30 07:57:44
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:2536 ms Tokens:26 时间:2026-08-30 07:57:45
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:2688 ms Tokens:26 时间:2026-08-30 07:57:47
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:7595 ms Tokens:27 时间:2026-08-30 07:57:45
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:4551 ms Tokens:26 时间:2026-08-30 07:57:50
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:5796 ms Tokens:26 时间:2026-08-30 07:57:53
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:4231 ms Tokens:26 时间:2026-08-30 07:57:55
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:3997 ms Tokens:211 时间:2026-08-30 07:57:59
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:6977 ms Tokens:386 时间:2026-08-30 07:57:59
JSON
{"status":"ok","message":"stable"}
#21 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3453 ms Tokens:189 时间:2026-08-30 07:58:03
JSON
{"status":"ok","message":"stable"}
#22 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:540 ms Tokens:- 时间:2026-08-30 07:58:06
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:529 ms Tokens:- 时间:2026-08-30 07:58:06
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:524 ms Tokens:- 时间:2026-08-30 07:58:06
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:471 ms Tokens:- 时间:2026-08-30 07:58:07
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:530 ms Tokens:- 时间:2026-08-30 07:58:07
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:519 ms Tokens:- 时间:2026-08-30 07:58:07
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:1899 ms Tokens:115 时间:2026-08-30 07:58:08
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:3168 ms Tokens:115 时间:2026-08-30 07:58:07
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2145 ms Tokens:115 时间:2026-08-30 07:58:10
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7134 ms Tokens:192 时间:2026-08-30 07:58:12
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:10925 ms Tokens:256 时间:2026-08-30 07:58:11
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1547 ms Tokens:153 时间:2026-08-30 07:58:21
JSON
无输出内容。
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1338 ms Tokens:153 时间:2026-08-30 07:58:23
JSON
无输出内容。
#35 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6486 ms Tokens:216 时间:2026-08-30 07:58:19
JSON
{"status":"ok","message":"stable"}
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1516 ms Tokens:153 时间:2026-08-30 07:58:24
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2080 ms Tokens:132 时间:2026-08-30 07:58:25
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1974 ms Tokens:128 时间:2026-08-30 07:58:26
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:207 ms Tokens:- 时间:2026-08-30 07:58:28
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:230 ms Tokens:- 时间:2026-08-30 07:58:28
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:177 ms Tokens:- 时间:2026-08-30 07:58:28
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:1975 ms Tokens:127 时间:2026-08-30 07:58:28
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:4365 ms Tokens:168 时间:2026-08-30 07:58:29
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:3805 ms Tokens:142 时间:2026-08-30 07:58:34
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:25947 ms Tokens:170 时间:2026-08-30 07:58:28
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 1077 200 113
DeepSeek-v4-pro-01 成功 1130 200 113
DeepSeek-v4-pro-03 成功 663 200 113
DeepSeek-v4-pro-01 成功 826 200 113
DeepSeek-v4-pro-03 成功 1066 200 113
DeepSeek-v4-pro-03 成功 1040 200 113
DeepSeek-v4-pro-04 成功 742 200 113
DeepSeek-v4-pro-04 成功 943 200 113
DeepSeek-v4-pro-04 成功 1018 200 113
DeepSeek-v4-pro-02 成功 1067 200 113
DeepSeek-v4-pro-02 成功 782 200 113
DeepSeek-v4-pro-02 成功 1033 200 113
jd-gemini-3.1-pro-preview 成功 2536 200 26
jd-gemini-3.1-pro-preview 成功 2688 200 26
jd-gemini-3.1-pro-preview 成功 7595 200 27
腾讯 Gemini 3.5 Flash 成功 4551 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 5796 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 4231 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 3997 200 211 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 6977 200 386 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 3453 200 189 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 540 403 - 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 524 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 471 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 530 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 519 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 1899 200 115
Kimi K3 - Aliyun Bailian 成功 3168 200 115
Kimi K3 - Aliyun Bailian 成功 2145 200 115
Kimi K3 成功 7134 200 192 {"status":"ok","message":"stable"}
Kimi K3 成功 10925 200 256 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1547 200 153
Kimi K3 - TopenRouter 成功 1338 200 153
Kimi K3 成功 6486 200 216 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1516 200 153
Qwen3.8-Max 成功 2080 200 132 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1974 200 128 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 207 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 230 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 177 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 1975 200 127 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4365 200 168 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3805 200 142 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 25947 200 170 {"status":"ok","message":"stable"}