历史详情

Run ID: 20260827-143908-0c3b6843

返回历史

测试结果

Run ID: 20260827-143908-0c3b6843

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3582 ms
P95 / Tokens7210 / 4448
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 1132 1284 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1199 1481 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1285 1427 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1437 1632 339
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2696 3035 79
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2854 3753 386
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 4154 5020 703
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 稳定 4315 4505 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5037 5670 537
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 可用 5663 8101 345
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 5712 7210 348
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 7508 9240 616
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:1194 ms Tokens:113 时间:2026-08-27 14:37:59
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1427 ms Tokens:113 时间:2026-08-27 14:37:59
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1235 ms Tokens:113 时间:2026-08-27 14:38:00
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1632 ms Tokens:113 时间:2026-08-27 14:38:00
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1265 ms Tokens:113 时间:2026-08-27 14:38:01
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1415 ms Tokens:113 时间:2026-08-27 14:38:02
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1481 ms Tokens:113 时间:2026-08-27 14:38:03
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:895 ms Tokens:113 时间:2026-08-27 14:38:04
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1221 ms Tokens:113 时间:2026-08-27 14:38:04
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1220 ms Tokens:113 时间:2026-08-27 14:38:04
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:893 ms Tokens:113 时间:2026-08-27 14:38:05
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1284 ms Tokens:113 时间:2026-08-27 14:38:06
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:3035 ms Tokens:27 时间:2026-08-27 14:38:06
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:2616 ms Tokens:26 时间:2026-08-27 14:38:07
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:2439 ms Tokens:26 时间:2026-08-27 14:38:09
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:4505 ms Tokens:26 时间:2026-08-27 14:38:10
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:4179 ms Tokens:26 时间:2026-08-27 14:38:12
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:4262 ms Tokens:26 时间:2026-08-27 14:38:14
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:3612 ms Tokens:206 时间:2026-08-27 14:38:16
JSON
```json {"status":"ok","message":"stable"} ```
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5020 ms Tokens:291 时间:2026-08-27 14:38:18
JSON
{"status":"ok","message":"stable"}
#21 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3830 ms Tokens:206 时间:2026-08-27 14:38:20
JSON
```json {"status":"ok","message":"stable"} ```
#22 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:535 ms Tokens:- 时间:2026-08-27 14:38:23
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:535 ms Tokens:- 时间:2026-08-27 14:38:23
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:510 ms Tokens:- 时间:2026-08-27 14:38:24
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:535 ms Tokens:- 时间:2026-08-27 14:38:24
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:475 ms Tokens:- 时间:2026-08-27 14:38:24
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:509 ms Tokens:- 时间:2026-08-27 14:38:25
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:6373 ms Tokens:115 时间:2026-08-27 14:38:25
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:8101 ms Tokens:115 时间:2026-08-27 14:38:25
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2515 ms Tokens:115 时间:2026-08-27 14:38:31
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7004 ms Tokens:186 时间:2026-08-27 14:38:33
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:9240 ms Tokens:228 时间:2026-08-27 14:38:34
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6281 ms Tokens:202 时间:2026-08-27 14:38:40
JSON
{"status":"ok","message":"stable"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:3932 ms Tokens:116 时间:2026-08-27 14:38:43
JSON
无输出内容。
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:5994 ms Tokens:116 时间:2026-08-27 14:38:47
JSON
无输出内容。
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:7210 ms Tokens:116 时间:2026-08-27 14:38:46
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2232 ms Tokens:125 时间:2026-08-27 14:38:53
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:3753 ms Tokens:131 时间:2026-08-27 14:38:53
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:175 ms Tokens:- 时间:2026-08-27 14:38:57
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:156 ms Tokens:- 时间:2026-08-27 14:38:57
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:155 ms Tokens:- 时间:2026-08-27 14:38:57
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:2579 ms Tokens:130 时间:2026-08-27 14:38:56
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:5670 ms Tokens:184 时间:2026-08-27 14:38:57
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:4772 ms Tokens:171 时间:2026-08-27 14:38:58
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:4669 ms Tokens:182 时间:2026-08-27 14:39:03
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 1194 200 113
DeepSeek-v4-pro-01 成功 1427 200 113
DeepSeek-v4-pro-01 成功 1235 200 113
DeepSeek-v4-pro-03 成功 1632 200 113
DeepSeek-v4-pro-03 成功 1265 200 113
DeepSeek-v4-pro-03 成功 1415 200 113
DeepSeek-v4-pro-04 成功 1481 200 113
DeepSeek-v4-pro-04 成功 895 200 113
DeepSeek-v4-pro-04 成功 1221 200 113
DeepSeek-v4-pro-02 成功 1220 200 113
DeepSeek-v4-pro-02 成功 893 200 113
DeepSeek-v4-pro-02 成功 1284 200 113
jd-gemini-3.1-pro-preview 成功 3035 200 27
jd-gemini-3.1-pro-preview 成功 2616 200 26
jd-gemini-3.1-pro-preview 成功 2439 200 26
腾讯 Gemini 3.5 Flash 成功 4505 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 4179 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 4262 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 3612 200 206 ```json {"status":"ok","message":"stable"} ```
qwen3.6-plus 成功 5020 200 291 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 3830 200 206 ```json {"status":"ok","message":"stable"} ```
pixflow-gemini-3.1-pro-preview 失败 535 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 535 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 510 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 535 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 475 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 509 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 6373 200 115
Kimi K3 - Aliyun Bailian 成功 8101 200 115
Kimi K3 - Aliyun Bailian 成功 2515 200 115
Kimi K3 成功 7004 200 186 {"status":"ok","message":"stable"}
Kimi K3 成功 9240 200 228 {"status":"ok","message":"stable"}
Kimi K3 成功 6281 200 202 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 3932 200 116
Kimi K3 - TopenRouter 成功 5994 200 116
Kimi K3 - TopenRouter 成功 7210 200 116
Qwen3.8-Max 成功 2232 200 125 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 3753 200 131 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 175 400 - 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
MiniMax H3 Context IR 失败 155 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2579 200 130 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5670 200 184 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4772 200 171 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4669 200 182 {"status":"ok","message":"stable"}