历史详情

Run ID: 20260827-154037-914791ad

返回历史

测试结果

Run ID: 20260827-154037-914791ad

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟4811 ms
P95 / Tokens11073 / 4485
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 968 1115 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1135 1299 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1227 1410 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1299 1397 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2388 3083 412
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 3120 3577 79
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 稳定 4252 4327 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 4856 6384 830
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5408 5559 466
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 7148 7689 686
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 22005 39889 348
Kimi K3 - Aliyun Bailian kimi/kimi-k3 2/3 1/3 66.67% 33.33% 不稳定 3488 4619 230 HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"c75701a7-a3bb-9411-9cbf-bae5219fb5df"}
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:752 ms Tokens:113 时间:2026-08-27 15:39:08
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1038 ms Tokens:113 时间:2026-08-27 15:39:08
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1115 ms Tokens:113 时间:2026-08-27 15:39:09
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:855 ms Tokens:113 时间:2026-08-27 15:39:09
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1251 ms Tokens:113 时间:2026-08-27 15:39:10
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1299 ms Tokens:113 时间:2026-08-27 15:39:10
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1233 ms Tokens:113 时间:2026-08-27 15:39:11
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1410 ms Tokens:113 时间:2026-08-27 15:39:11
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1040 ms Tokens:113 时间:2026-08-27 15:39:12
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1397 ms Tokens:113 时间:2026-08-27 15:39:13
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1248 ms Tokens:113 时间:2026-08-27 15:39:13
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1254 ms Tokens:113 时间:2026-08-27 15:39:14
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:2655 ms Tokens:27 时间:2026-08-27 15:39:15
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:3577 ms Tokens:26 时间:2026-08-27 15:39:15
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:3130 ms Tokens:26 时间:2026-08-27 15:39:18
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:4322 ms Tokens:26 时间:2026-08-27 15:39:18
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4108 ms Tokens:26 时间:2026-08-27 15:39:21
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:4327 ms Tokens:26 时间:2026-08-27 15:39:23
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:4606 ms Tokens:259 时间:2026-08-27 15:39:25
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3580 ms Tokens:201 时间:2026-08-27 15:39:27
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:503 ms Tokens:- 时间:2026-08-27 15:39:30
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:513 ms Tokens:- 时间:2026-08-27 15:39:31
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:542 ms Tokens:- 时间:2026-08-27 15:39:31
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:554 ms Tokens:- 时间:2026-08-27 15:39:32
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:460 ms Tokens:- 时间:2026-08-27 15:39:33
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:2026-08-27 15:39:33
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2357 ms Tokens:115 时间:2026-08-27 15:39:34
JSON
无输出内容。
#28 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:6384 ms Tokens:370 时间:2026-08-27 15:39:30
JSON
{"status":"ok","message":"stable"}
#29 Kimi K3 - Aliyun Bailian 失败 HTTP 429
模型:kimi/kimi-k3 延迟:1459 ms Tokens:- 时间:2026-08-27 15:39:36
JSON
HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"c75701a7-a3bb-9411-9cbf-bae5219fb5df"}
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:4619 ms Tokens:115 时间:2026-08-27 15:39:36
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7531 ms Tokens:187 时间:2026-08-27 15:39:37
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6226 ms Tokens:221 时间:2026-08-27 15:39:41
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7689 ms Tokens:278 时间:2026-08-27 15:39:45
JSON
{"status":"ok","message":"stable"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:15054 ms Tokens:116 时间:2026-08-27 15:39:47
JSON
无输出内容。
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:11073 ms Tokens:116 时间:2026-08-27 15:40:02
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1994 ms Tokens:138 时间:2026-08-27 15:40:13
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2088 ms Tokens:128 时间:2026-08-27 15:40:15
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:3083 ms Tokens:146 时间:2026-08-27 15:40:17
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:201 ms Tokens:- 时间:2026-08-27 15:40:20
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:197 ms Tokens:- 时间:2026-08-27 15:40:20
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:156 ms Tokens:- 时间:2026-08-27 15:40:21
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:5138 ms Tokens:165 时间:2026-08-27 15:40:21
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:5559 ms Tokens:159 时间:2026-08-27 15:40:26
JSON
{"status":"ok","message":"stable"}
#44 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:39889 ms Tokens:116 时间:2026-08-27 15:39:53
JSON
无输出内容。
#45 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:5528 ms Tokens:142 时间:2026-08-27 15:40:31
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 752 200 113
DeepSeek-v4-pro-01 成功 1038 200 113
DeepSeek-v4-pro-01 成功 1115 200 113
DeepSeek-v4-pro-03 成功 855 200 113
DeepSeek-v4-pro-03 成功 1251 200 113
DeepSeek-v4-pro-03 成功 1299 200 113
DeepSeek-v4-pro-04 成功 1233 200 113
DeepSeek-v4-pro-04 成功 1410 200 113
DeepSeek-v4-pro-04 成功 1040 200 113
DeepSeek-v4-pro-02 成功 1397 200 113
DeepSeek-v4-pro-02 成功 1248 200 113
DeepSeek-v4-pro-02 成功 1254 200 113
jd-gemini-3.1-pro-preview 成功 2655 200 27
jd-gemini-3.1-pro-preview 成功 3577 200 26
jd-gemini-3.1-pro-preview 成功 3130 200 26
腾讯 Gemini 3.5 Flash 成功 4322 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 4108 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 4327 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 4606 200 259 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 3580 200 201 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 503 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 513 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 542 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 554 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 460 403 - 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"}
Kimi K3 - Aliyun Bailian 成功 2357 200 115
qwen3.6-plus 成功 6384 200 370 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 失败 1459 429 - HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"c75701a7-a3bb-9411-9cbf-bae5219fb5df"}
Kimi K3 - Aliyun Bailian 成功 4619 200 115
Kimi K3 成功 7531 200 187 {"status":"ok","message":"stable"}
Kimi K3 成功 6226 200 221 {"status":"ok","message":"stable"}
Kimi K3 成功 7689 200 278 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 15054 200 116
Kimi K3 - TopenRouter 成功 11073 200 116
Qwen3.8-Max 成功 1994 200 138 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2088 200 128 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 3083 200 146 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 201 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 197 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 156 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 5138 200 165 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5559 200 159 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 39889 200 116
yulin-gemini-3.7-flash-high 成功 5528 200 142 {"status":"ok","message":"stable"}