历史详情

Run ID: 20260827-194642-8dd59500

返回历史

测试结果

Run ID: 20260827-194642-8dd59500

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟3742 ms
P95 / Tokens6669 / 4492
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-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1074 1479 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1228 1246 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1439 2037 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1519 1664 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1813 2064 399
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1875 2105 345
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 3245 4285 422
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 稳定 4036 4632 683
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4964 6235 509
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5158 5686 78
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 6534 7254 647
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 2/3 1/3 66.67% 33.33% 不稳定 16163 30112 53 timeout: The read operation timed out
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:1000 ms Tokens:113 时间:2026-08-27 19:45:19
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:2037 ms Tokens:113 时间:2026-08-27 19:45:19
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1281 ms Tokens:113 时间:2026-08-27 19:45:20
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:886 ms Tokens:113 时间:2026-08-27 19:45:21
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1479 ms Tokens:113 时间:2026-08-27 19:45:21
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:858 ms Tokens:113 时间:2026-08-27 19:45:21
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1487 ms Tokens:113 时间:2026-08-27 19:45:22
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1664 ms Tokens:113 时间:2026-08-27 19:45:22
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1406 ms Tokens:113 时间:2026-08-27 19:45:24
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1230 ms Tokens:113 时间:2026-08-27 19:45:24
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1208 ms Tokens:113 时间:2026-08-27 19:45:25
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1246 ms Tokens:113 时间:2026-08-27 19:45:25
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:30112 ms Tokens:27 时间:2026-08-27 19:45:26
JSON
无输出内容。
#14 jd-gemini-3.1-pro-preview 失败 HTTP -
模型:gemini-3.1-pro-preview 延迟:30250 ms Tokens:- 时间:2026-08-27 19:45:26
JSON
timeout: The read operation timed out
#15 jd-gemini-3.1-pro-preview 成功 HTTP 200
模型:gemini-3.1-pro-preview 延迟:2215 ms Tokens:26 时间:2026-08-27 19:45:57
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:5269 ms Tokens:26 时间:2026-08-27 19:45:57
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:5686 ms Tokens:26 时间:2026-08-27 19:45:59
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:4519 ms Tokens:26 时间:2026-08-27 19:46:02
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:3825 ms Tokens:209 时间:2026-08-27 19:46:04
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4632 ms Tokens:268 时间:2026-08-27 19:46:07
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:583 ms Tokens:- 时间:2026-08-27 19:46:11
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#22 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3651 ms Tokens:206 时间:2026-08-27 19:46:08
JSON
{"status":"ok","message":"stable"}
#23 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 19:46:12
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:508 ms Tokens:- 时间:2026-08-27 19:46:12
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:501 ms Tokens:- 时间:2026-08-27 19:46:12
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:543 ms Tokens:- 时间:2026-08-27 19:46:12
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:503 ms Tokens:- 时间:2026-08-27 19:46:13
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:1707 ms Tokens:115 时间:2026-08-27 19:46:13
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2105 ms Tokens:115 时间:2026-08-27 19:46:13
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1815 ms Tokens:115 时间:2026-08-27 19:46:15
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7254 ms Tokens:248 时间:2026-08-27 19:46:15
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6669 ms Tokens:198 时间:2026-08-27 19:46:17
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:3267 ms Tokens:153 时间:2026-08-27 19:46:23
JSON
无输出内容。
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5680 ms Tokens:201 时间:2026-08-27 19:46:22
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2184 ms Tokens:153 时间:2026-08-27 19:46:27
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1712 ms Tokens:128 时间:2026-08-27 19:46:29
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:4285 ms Tokens:116 时间:2026-08-27 19:46:28
JSON
无输出内容。
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2064 ms Tokens:140 时间:2026-08-27 19:46:31
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:223 ms Tokens:- 时间:2026-08-27 19:46:33
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:198 ms Tokens:- 时间:2026-08-27 19:46:33
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:2026-08-27 19:46:33
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:1664 ms Tokens:131 时间:2026-08-27 19:46:32
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:5022 ms Tokens:174 时间:2026-08-27 19:46:33
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:6235 ms Tokens:183 时间:2026-08-27 19:46:34
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:3636 ms Tokens:152 时间:2026-08-27 19:46:38
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 1000 200 113
DeepSeek-v4-pro-01 成功 2037 200 113
DeepSeek-v4-pro-01 成功 1281 200 113
DeepSeek-v4-pro-03 成功 886 200 113
DeepSeek-v4-pro-03 成功 1479 200 113
DeepSeek-v4-pro-03 成功 858 200 113
DeepSeek-v4-pro-04 成功 1487 200 113
DeepSeek-v4-pro-04 成功 1664 200 113
DeepSeek-v4-pro-04 成功 1406 200 113
DeepSeek-v4-pro-02 成功 1230 200 113
DeepSeek-v4-pro-02 成功 1208 200 113
DeepSeek-v4-pro-02 成功 1246 200 113
jd-gemini-3.1-pro-preview 成功 30112 200 27
jd-gemini-3.1-pro-preview 失败 30250 - - timeout: The read operation timed out
jd-gemini-3.1-pro-preview 成功 2215 200 26
腾讯 Gemini 3.5 Flash 成功 5269 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 5686 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 4519 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 3825 200 209 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 4632 200 268 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 583 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 3651 200 206 {"status":"ok","message":"stable"}
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 508 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 501 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 543 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 503 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 1707 200 115
Kimi K3 - Aliyun Bailian 成功 2105 200 115
Kimi K3 - Aliyun Bailian 成功 1815 200 115
Kimi K3 成功 7254 200 248 {"status":"ok","message":"stable"}
Kimi K3 成功 6669 200 198 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 3267 200 153
Kimi K3 成功 5680 200 201 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2184 200 153
Qwen3.8-Max 成功 1712 200 128 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 4285 200 116
Qwen3.8-Max 成功 2064 200 140 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 223 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 198 400 - 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
Qwen3.8-Max 成功 1664 200 131 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5022 200 174 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 6235 200 183 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3636 200 152 {"status":"ok","message":"stable"}