历史详情

Run ID: 20260829-164246-20db3c4b

返回历史

测试结果

Run ID: 20260829-164246-20db3c4b

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3394 ms
P95 / Tokens7530 / 4489
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 1112 1366 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1173 1380 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1312 1367 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1334 1484 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1818 2768 345
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 1839 2142 379
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 1971 2097 78
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 3197 4827 345
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 稳定 4301 4393 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5622 6478 472
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5827 7530 1001
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 11228 19195 435
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:1158 ms Tokens:113 时间:2026-08-29 16:41:40
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1366 ms Tokens:113 时间:2026-08-29 16:41:40
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:812 ms Tokens:113 时间:2026-08-29 16:41:41
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1298 ms Tokens:113 时间:2026-08-29 16:41:42
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1221 ms Tokens:113 时间:2026-08-29 16:41:42
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1484 ms Tokens:113 时间:2026-08-29 16:41:43
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1112 ms Tokens:113 时间:2026-08-29 16:41:43
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1029 ms Tokens:113 时间:2026-08-29 16:41:44
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1380 ms Tokens:113 时间:2026-08-29 16:41:45
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1367 ms Tokens:113 时间:2026-08-29 16:41:45
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1276 ms Tokens:113 时间:2026-08-29 16:41:46
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1295 ms Tokens:113 时间:2026-08-29 16:41:47
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:1954 ms Tokens:26 时间:2026-08-29 16:41:47
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:2097 ms Tokens:26 时间:2026-08-29 16:41:48
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:1862 ms Tokens:26 时间:2026-08-29 16:41:49
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:4349 ms Tokens:26 时间:2026-08-29 16:41:50
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:4161 ms Tokens:26 时间:2026-08-29 16:41:51
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:4393 ms Tokens:26 时间:2026-08-29 16:41:55
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:4091 ms Tokens:231 时间:2026-08-29 16:41:55
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5862 ms Tokens:336 时间:2026-08-29 16:41:59
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:512 ms Tokens:- 时间:2026-08-29 16:42:05
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:520 ms Tokens:- 时间:2026-08-29 16:42:05
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:522 ms Tokens:- 时间:2026-08-29 16:42:06
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:7530 ms Tokens:434 时间:2026-08-29 16:41:59
JSON
{"status":"ok","message":"stable"}
#25 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:484 ms Tokens:- 时间:2026-08-29 16:42:06
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:479 ms Tokens:- 时间:2026-08-29 16:42:07
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:499 ms Tokens:- 时间:2026-08-29 16:42:07
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:2631 ms Tokens:115 时间:2026-08-29 16:42:07
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2133 ms Tokens:115 时间:2026-08-29 16:42:10
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:4827 ms Tokens:115 时间:2026-08-29 16:42:07
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5932 ms Tokens:115 时间:2026-08-29 16:42:12
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8559 ms Tokens:115 时间:2026-08-29 16:42:18
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1386 ms Tokens:115 时间:2026-08-29 16:42:27
JSON
{"status":"
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2768 ms Tokens:115 时间:2026-08-29 16:42:28
JSON
无输出内容。
#35 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:19195 ms Tokens:205 时间:2026-08-29 16:42:12
JSON
{"status":"ok","message":"stable"}
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1300 ms Tokens:115 时间:2026-08-29 16:42:31
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1555 ms Tokens:128 时间:2026-08-29 16:42:31
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2142 ms Tokens:125 时间:2026-08-29 16:42:32
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:240 ms Tokens:- 时间:2026-08-29 16:42:34
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:1820 ms Tokens:126 时间:2026-08-29 16:42:33
JSON
{"status":"ok","message":"stable"}
#41 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:175 ms Tokens:- 时间:2026-08-29 16:42:35
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:194 ms Tokens:- 时间:2026-08-29 16:42:35
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:5181 ms Tokens:161 时间:2026-08-29 16:42:35
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:5207 ms Tokens:142 时间:2026-08-29 16:42:35
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:6478 ms Tokens:169 时间:2026-08-29 16:42:40
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 1158 200 113
DeepSeek-v4-pro-01 成功 1366 200 113
DeepSeek-v4-pro-01 成功 812 200 113
DeepSeek-v4-pro-03 成功 1298 200 113
DeepSeek-v4-pro-03 成功 1221 200 113
DeepSeek-v4-pro-03 成功 1484 200 113
DeepSeek-v4-pro-04 成功 1112 200 113
DeepSeek-v4-pro-04 成功 1029 200 113
DeepSeek-v4-pro-04 成功 1380 200 113
DeepSeek-v4-pro-02 成功 1367 200 113
DeepSeek-v4-pro-02 成功 1276 200 113
DeepSeek-v4-pro-02 成功 1295 200 113
jd-gemini-3.1-pro-preview 成功 1954 200 26
jd-gemini-3.1-pro-preview 成功 2097 200 26
jd-gemini-3.1-pro-preview 成功 1862 200 26
腾讯 Gemini 3.5 Flash 成功 4349 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 4161 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 4393 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 4091 200 231 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 5862 200 336 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 512 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 520 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 522 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 7530 200 434 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 484 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 479 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 499 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 2631 200 115
Kimi K3 - Aliyun Bailian 成功 2133 200 115
Kimi K3 - Aliyun Bailian 成功 4827 200 115
Kimi K3 成功 5932 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 8559 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 1386 200 115 {"status":"
Kimi K3 - TopenRouter 成功 2768 200 115
Kimi K3 成功 19195 200 205 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1300 200 115
Qwen3.8-Max 成功 1555 200 128 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2142 200 125 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 240 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 1820 200 126 {"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 194 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 5181 200 161 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5207 200 142 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 6478 200 169 {"status":"ok","message":"stable"}