历史详情

Run ID: 20260830-201102-9271f5d6

返回历史

测试结果

Run ID: 20260830-201102-9271f5d6

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3202 ms
P95 / Tokens6800 / 4875
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 1231 1318 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1500 1590 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1591 2005 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1651 1939 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1923 2269 416
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2045 2501 383
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2108 2293 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 3172 3438 79
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4509 5100 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5126 5428 482
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 6430 10359 548
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 7135 10762 1188
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:1406 ms Tokens:113 时间:2026-08-30 20:10:00
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:2005 ms Tokens:113 时间:2026-08-30 20:10:00
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1363 ms Tokens:113 时间:2026-08-30 20:10:02
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1590 ms Tokens:113 时间:2026-08-30 20:10:02
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1579 ms Tokens:113 时间:2026-08-30 20:10:03
JSON
{"status":"
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1332 ms Tokens:113 时间:2026-08-30 20:10:04
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1547 ms Tokens:113 时间:2026-08-30 20:10:04
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1939 ms Tokens:113 时间:2026-08-30 20:10:05
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1468 ms Tokens:113 时间:2026-08-30 20:10:06
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1116 ms Tokens:113 时间:2026-08-30 20:10:07
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1260 ms Tokens:113 时间:2026-08-30 20:10:08
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1318 ms Tokens:113 时间:2026-08-30 20:10:08
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:3188 ms Tokens:26 时间:2026-08-30 20:10:09
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:3438 ms Tokens:27 时间:2026-08-30 20:10:09
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:2891 ms Tokens:26 时间:2026-08-30 20:10:12
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:5100 ms Tokens:26 时间:2026-08-30 20:10:13
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4216 ms Tokens:26 时间:2026-08-30 20:10:15
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:4212 ms Tokens:26 时间:2026-08-30 20:10:18
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:3843 ms Tokens:193 时间:2026-08-30 20:10:19
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:6800 ms Tokens:378 时间:2026-08-30 20:10:22
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:534 ms Tokens:- 时间:2026-08-30 20:10:29
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:480 ms Tokens:- 时间:2026-08-30 20:10:30
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:518 ms Tokens:- 时间:2026-08-30 20:10:30
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:520 ms Tokens:- 时间:2026-08-30 20:10:31
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:550 ms Tokens:- 时间:2026-08-30 20:10:31
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:448 ms Tokens:- 时间:2026-08-30 20:10:32
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:10762 ms Tokens:617 时间:2026-08-30 20:10:23
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1954 ms Tokens:115 时间:2026-08-30 20:10:32
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2079 ms Tokens:115 时间:2026-08-30 20:10:34
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2293 ms Tokens:115 时间:2026-08-30 20:10:34
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:3897 ms Tokens:151 时间:2026-08-30 20:10:36
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5034 ms Tokens:173 时间:2026-08-30 20:10:36
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2421 ms Tokens:115 时间:2026-08-30 20:10:41
JSON
{"status":"ok","message":"
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1215 ms Tokens:153 时间:2026-08-30 20:10:43
JSON
无输出内容。
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2501 ms Tokens:115 时间:2026-08-30 20:10:44
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1770 ms Tokens:136 时间:2026-08-30 20:10:47
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1730 ms Tokens:136 时间:2026-08-30 20:10:49
JSON
{"status":"ok","message":"stable"}
#38 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:10359 ms Tokens:224 时间:2026-08-30 20:10:40
JSON
```json {"status":"ok","message":"stable"} ```
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:168 ms Tokens:- 时间:2026-08-30 20:10:51
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:203 ms Tokens:- 时间:2026-08-30 20:10:51
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:189 ms Tokens:- 时间:2026-08-30 20:10:51
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:2269 ms Tokens:144 时间:2026-08-30 20:10:50
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:5428 ms Tokens:156 时间:2026-08-30 20:10:51
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:4827 ms Tokens:153 时间:2026-08-30 20:10:53
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:5123 ms Tokens:173 时间:2026-08-30 20:10:57
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 1406 200 113
DeepSeek-v4-pro-01 成功 2005 200 113
DeepSeek-v4-pro-01 成功 1363 200 113
DeepSeek-v4-pro-03 成功 1590 200 113
DeepSeek-v4-pro-03 成功 1579 200 113 {"status":"
DeepSeek-v4-pro-03 成功 1332 200 113
DeepSeek-v4-pro-04 成功 1547 200 113
DeepSeek-v4-pro-04 成功 1939 200 113
DeepSeek-v4-pro-04 成功 1468 200 113
DeepSeek-v4-pro-02 成功 1116 200 113
DeepSeek-v4-pro-02 成功 1260 200 113
DeepSeek-v4-pro-02 成功 1318 200 113
jd-gemini-3.1-pro-preview 成功 3188 200 26
jd-gemini-3.1-pro-preview 成功 3438 200 27
jd-gemini-3.1-pro-preview 成功 2891 200 26
腾讯 Gemini 3.5 Flash 成功 5100 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 4216 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 4212 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 3843 200 193 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 6800 200 378 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 534 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 480 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 518 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 520 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 550 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 448 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 10762 200 617 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 1954 200 115
Kimi K3 - Aliyun Bailian 成功 2079 200 115
Kimi K3 - Aliyun Bailian 成功 2293 200 115
Kimi K3 成功 3897 200 151 {"status":"ok","message":"stable"}
Kimi K3 成功 5034 200 173 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2421 200 115 {"status":"ok","message":"
Kimi K3 - TopenRouter 成功 1215 200 153
Kimi K3 - TopenRouter 成功 2501 200 115
Qwen3.8-Max 成功 1770 200 136 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1730 200 136 {"status":"ok","message":"stable"}
Kimi K3 成功 10359 200 224 ```json {"status":"ok","message":"stable"} ```
MiniMax H3 Context IR 失败 168 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 203 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 189 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2269 200 144 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5428 200 156 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4827 200 153 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5123 200 173 {"status":"ok","message":"stable"}