历史详情

Run ID: 20260831-041909-afbc1c53

返回历史

测试结果

Run ID: 20260831-041909-afbc1c53

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟2773 ms
P95 / Tokens5996 / 4437
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 964 1062 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 973 1085 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1084 1335 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1172 1283 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1843 2089 383
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1927 2360 383
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1986 2198 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2990 3103 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 4408 6601 760
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4566 5147 464
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5614 5904 590
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5749 6748 78
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:788 ms Tokens:113 时间:2026-08-31 04:18:15
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1062 ms Tokens:113 时间:2026-08-31 04:18:15
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1043 ms Tokens:113 时间:2026-08-31 04:18:16
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1335 ms Tokens:113 时间:2026-08-31 04:18:16
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:928 ms Tokens:113 时间:2026-08-31 04:18:17
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:991 ms Tokens:113 时间:2026-08-31 04:18:18
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:807 ms Tokens:113 时间:2026-08-31 04:18:18
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1028 ms Tokens:113 时间:2026-08-31 04:18:19
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1085 ms Tokens:113 时间:2026-08-31 04:18:19
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1073 ms Tokens:113 时间:2026-08-31 04:18:20
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1283 ms Tokens:113 时间:2026-08-31 04:18:20
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1160 ms Tokens:113 时间:2026-08-31 04:18:21
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:3103 ms Tokens:26 时间:2026-08-31 04:18:21
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:2976 ms Tokens:26 时间:2026-08-31 04:18:22
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:2893 ms Tokens:26 时间:2026-08-31 04:18:24
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:6748 ms Tokens:26 时间:2026-08-31 04:18:25
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:5996 ms Tokens:26 时间:2026-08-31 04:18:27
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:4503 ms Tokens:26 时间:2026-08-31 04:18:32
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:3286 ms Tokens:189 时间:2026-08-31 04:18:33
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3337 ms Tokens:189 时间:2026-08-31 04:18:36
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:522 ms Tokens:- 时间:2026-08-31 04:18:40
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:525 ms Tokens:- 时间:2026-08-31 04:18:40
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:2026-08-31 04:18:41
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:523 ms Tokens:- 时间:2026-08-31 04:18:41
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:483 ms Tokens:- 时间:2026-08-31 04:18:42
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#26 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:6601 ms Tokens:382 时间:2026-08-31 04:18:36
JSON
{"status":"ok","message":"stable"}
#27 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:457 ms Tokens:- 时间:2026-08-31 04:18:42
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:1805 ms Tokens:115 时间:2026-08-31 04:18:43
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1957 ms Tokens:115 时间:2026-08-31 04:18:43
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2198 ms Tokens:115 时间:2026-08-31 04:18:44
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5904 ms Tokens:203 时间:2026-08-31 04:18:45
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5544 ms Tokens:191 时间:2026-08-31 04:18:47
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1118 ms Tokens:153 时间:2026-08-31 04:18:52
JSON
无输出内容。
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2360 ms Tokens:115 时间:2026-08-31 04:18:53
JSON
{"status
#35 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5396 ms Tokens:196 时间:2026-08-31 04:18:51
JSON
{"status":"ok","message":"stable"}
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1762 ms Tokens:123 时间:2026-08-31 04:18:56
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2303 ms Tokens:115 时间:2026-08-31 04:18:56
JSON
无输出内容。
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1679 ms Tokens:126 时间:2026-08-31 04:18:58
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:174 ms Tokens:- 时间:2026-08-31 04:19:00
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#40 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2089 ms Tokens:134 时间:2026-08-31 04:18:58
JSON
{"status":"ok","message":"stable"}
#41 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:174 ms Tokens:- 时间:2026-08-31 04:19:00
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:192 ms Tokens:- 时间:2026-08-31 04:19:00
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#43 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:4612 ms Tokens:156 时间:2026-08-31 04:19:00
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:5147 ms Tokens:153 时间:2026-08-31 04:19:00
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:3940 ms Tokens:155 时间:2026-08-31 04:19:05
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 788 200 113
DeepSeek-v4-pro-01 成功 1062 200 113
DeepSeek-v4-pro-01 成功 1043 200 113
DeepSeek-v4-pro-03 成功 1335 200 113
DeepSeek-v4-pro-03 成功 928 200 113
DeepSeek-v4-pro-03 成功 991 200 113
DeepSeek-v4-pro-04 成功 807 200 113
DeepSeek-v4-pro-04 成功 1028 200 113
DeepSeek-v4-pro-04 成功 1085 200 113
DeepSeek-v4-pro-02 成功 1073 200 113
DeepSeek-v4-pro-02 成功 1283 200 113
DeepSeek-v4-pro-02 成功 1160 200 113
jd-gemini-3.1-pro-preview 成功 3103 200 26
jd-gemini-3.1-pro-preview 成功 2976 200 26
jd-gemini-3.1-pro-preview 成功 2893 200 26
腾讯 Gemini 3.5 Flash 成功 6748 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 5996 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 4503 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 3286 200 189 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 3337 200 189 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 522 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 525 403 - 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 523 403 - 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"}
qwen3.6-plus 成功 6601 200 382 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 457 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 1805 200 115
Kimi K3 - Aliyun Bailian 成功 1957 200 115
Kimi K3 - Aliyun Bailian 成功 2198 200 115
Kimi K3 成功 5904 200 203 {"status":"ok","message":"stable"}
Kimi K3 成功 5544 200 191 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1118 200 153
Kimi K3 - TopenRouter 成功 2360 200 115 {"status
Kimi K3 成功 5396 200 196 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1762 200 123 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2303 200 115
Qwen3.8-Max 成功 1679 200 126 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 174 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2089 200 134 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 174 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 192 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 4612 200 156 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5147 200 153 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3940 200 155 {"status":"ok","message":"stable"}