历史详情

Run ID: 20260830-085955-88f8214a

返回历史

测试结果

Run ID: 20260830-085955-88f8214a

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3199 ms
P95 / Tokens8334 / 5056
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 983 1088 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1046 1184 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1178 1330 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1263 1413 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1934 2041 380
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 稳定 2349 2784 455
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2504 2859 459
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2593 2778 78
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2698 3327 345
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5700 7331 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 6891 8046 1196
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 9253 10287 709
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:1062 ms Tokens:113 时间:2026-08-30 08:58:55
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1330 ms Tokens:113 时间:2026-08-30 08:58:55
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 08:58:56
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1034 ms Tokens:113 时间:2026-08-30 08:58:56
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1413 ms Tokens:113 时间:2026-08-30 08:58:57
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1344 ms Tokens:113 时间:2026-08-30 08:58:57
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:876 ms Tokens:113 时间:2026-08-30 08:58:58
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1184 ms Tokens:113 时间:2026-08-30 08:58:58
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1080 ms Tokens:113 时间:2026-08-30 08:58:59
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1009 ms Tokens:113 时间:2026-08-30 08:58:59
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:852 ms Tokens:113 时间:2026-08-30 08:59:00
JSON
{"status":"ok","message
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1088 ms Tokens:113 时间:2026-08-30 08:59:00
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:2778 ms Tokens:26 时间:2026-08-30 08:59:01
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:2755 ms Tokens:26 时间:2026-08-30 08:59:01
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:2247 ms Tokens:26 时间:2026-08-30 08:59:04
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:4360 ms Tokens:26 时间:2026-08-30 08:59:04
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:7331 ms Tokens:26 时间:2026-08-30 08:59:06
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 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5409 ms Tokens:26 时间:2026-08-30 08:59:09
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:4596 ms Tokens:264 时间:2026-08-30 08:59:14
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:8033 ms Tokens:466 时间:2026-08-30 08:59:14
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:539 ms Tokens:- 时间:2026-08-30 08:59:22
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:524 ms Tokens:- 时间:2026-08-30 08:59:22
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:524 ms Tokens:- 时间:2026-08-30 08:59:23
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:483 ms Tokens:- 时间:2026-08-30 08:59:23
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:438 ms Tokens:- 时间:2026-08-30 08:59:24
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:449 ms Tokens:- 时间:2026-08-30 08:59:24
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:8046 ms Tokens:466 时间:2026-08-30 08:59:19
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2991 ms Tokens:115 时间:2026-08-30 08:59:25
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1776 ms Tokens:115 时间:2026-08-30 08:59:27
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:3327 ms Tokens:115 时间:2026-08-30 08:59:28
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:9140 ms Tokens:193 时间:2026-08-30 08:59:28
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:10287 ms Tokens:204 时间:2026-08-30 08:59:31
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2354 ms Tokens:153 时间:2026-08-30 08:59:41
JSON
无输出内容。
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8334 ms Tokens:312 时间:2026-08-30 08:59:37
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2300 ms Tokens:153 时间:2026-08-30 08:59:44
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1790 ms Tokens:126 时间:2026-08-30 08:59:46
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2859 ms Tokens:153 时间:2026-08-30 08:59:46
JSON
无输出内容。
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1972 ms Tokens:126 时间:2026-08-30 08:59:48
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:188 ms Tokens:- 时间:2026-08-30 08:59:50
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:186 ms Tokens:- 时间:2026-08-30 08:59:50
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:167 ms Tokens:- 时间:2026-08-30 08:59:50
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:2041 ms Tokens:128 时间:2026-08-30 08:59:49
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:2195 ms Tokens:137 时间:2026-08-30 08:59:51
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:2784 ms Tokens:180 时间:2026-08-30 08:59:50
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:2068 ms Tokens:138 时间:2026-08-30 08:59:53
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 1062 200 113
DeepSeek-v4-pro-01 成功 1330 200 113
DeepSeek-v4-pro-01 成功 1142 200 113
DeepSeek-v4-pro-03 成功 1034 200 113
DeepSeek-v4-pro-03 成功 1413 200 113
DeepSeek-v4-pro-03 成功 1344 200 113
DeepSeek-v4-pro-04 成功 876 200 113
DeepSeek-v4-pro-04 成功 1184 200 113
DeepSeek-v4-pro-04 成功 1080 200 113
DeepSeek-v4-pro-02 成功 1009 200 113
DeepSeek-v4-pro-02 成功 852 200 113 {"status":"ok","message
DeepSeek-v4-pro-02 成功 1088 200 113
jd-gemini-3.1-pro-preview 成功 2778 200 26
jd-gemini-3.1-pro-preview 成功 2755 200 26
jd-gemini-3.1-pro-preview 成功 2247 200 26
腾讯 Gemini 3.5 Flash 成功 4360 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 7331 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 5409 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 4596 200 264 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 8033 200 466 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 539 403 - 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"}
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 483 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 438 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 449 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 8046 200 466 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 2991 200 115
Kimi K3 - Aliyun Bailian 成功 1776 200 115
Kimi K3 - Aliyun Bailian 成功 3327 200 115
Kimi K3 成功 9140 200 193 {"status":"ok","message":"stable"}
Kimi K3 成功 10287 200 204 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2354 200 153
Kimi K3 成功 8334 200 312 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2300 200 153
Qwen3.8-Max 成功 1790 200 126 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2859 200 153
Qwen3.8-Max 成功 1972 200 126 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 188 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 186 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 167 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2041 200 128 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2195 200 137 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2784 200 180 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2068 200 138 {"status":"ok","message":"stable"}