历史详情

Run ID: 20260829-174400-39d8d509

返回历史

测试结果

Run ID: 20260829-174400-39d8d509

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟3118 ms
P95 / Tokens6141 / 4415
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-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1015 1179 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1041 1234 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1202 1237 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1224 1323 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2148 2439 345
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2194 2751 339
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2785 3466 345
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 稳定 4337 4678 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5005 7225 813
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5045 5327 489
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5453 6141 597
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 2/3 1/3 66.67% 33.33% 不稳定 7389 11029 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:1129 ms Tokens:113 时间:2026-08-29 17:42:47
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1323 ms Tokens:113 时间:2026-08-29 17:42:47
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1222 ms Tokens:113 时间:2026-08-29 17:42:48
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1136 ms Tokens:113 时间:2026-08-29 17:42:48
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1233 ms Tokens:113 时间:2026-08-29 17:42:49
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1237 ms Tokens:113 时间:2026-08-29 17:42:49
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1179 ms Tokens:113 时间:2026-08-29 17:42:50
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1154 ms Tokens:113 时间:2026-08-29 17:42:50
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:714 ms Tokens:113 时间:2026-08-29 17:42:51
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:843 ms Tokens:113 时间:2026-08-29 17:42:51
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1048 ms Tokens:113 时间:2026-08-29 17:42:52
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1234 ms Tokens:113 时间:2026-08-29 17:42:52
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:11029 ms Tokens:26 时间:2026-08-29 17:42:53
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:3750 ms Tokens:27 时间:2026-08-29 17:43:05
JSON
无输出内容。
#15 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4109 ms Tokens:26 时间:2026-08-29 17:43:08
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
#16 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4678 ms Tokens:26 时间:2026-08-29 17:43:12
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4226 ms Tokens:26 时间:2026-08-29 17:43:17
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 jd-gemini-3.1-pro-preview 失败 HTTP -
模型:gemini-3.1-pro-preview 延迟:30255 ms Tokens:- 时间:2026-08-29 17:42:53
JSON
timeout: The read operation timed out
#19 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4152 ms Tokens:222 时间:2026-08-29 17:43:21
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3640 ms Tokens:202 时间:2026-08-29 17:43:25
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:588 ms Tokens:- 时间:2026-08-29 17:43:29
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:486 ms Tokens:- 时间:2026-08-29 17:43:30
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#23 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:7225 ms Tokens:389 时间:2026-08-29 17:43:23
JSON
{"status":"ok","message":"stable"}
#24 pixflow-gemini-3.1-pro-preview 失败 HTTP 403
模型:gemini-3.1-pro-preview 延迟:547 ms Tokens:- 时间:2026-08-29 17:43:30
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:442 ms Tokens:- 时间:2026-08-29 17:43:31
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:492 ms Tokens:- 时间:2026-08-29 17:43:31
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:484 ms Tokens:- 时间:2026-08-29 17:43:31
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:2282 ms Tokens:115 时间:2026-08-29 17:43:31
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2607 ms Tokens:115 时间:2026-08-29 17:43:31
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:3466 ms Tokens:115 时间:2026-08-29 17:43:34
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6141 ms Tokens:187 时间:2026-08-29 17:43:34
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:4724 ms Tokens:185 时间:2026-08-29 17:43:37
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2439 ms Tokens:115 时间:2026-08-29 17:43:42
JSON
{"status":"ok","
#34 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5495 ms Tokens:225 时间:2026-08-29 17:43:40
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1967 ms Tokens:115 时间:2026-08-29 17:43:44
JSON
无输出内容。
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2040 ms Tokens:115 时间:2026-08-29 17:43:45
JSON
{"status":"ok","message":"stable
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1408 ms Tokens:81 时间:2026-08-29 17:43:46
JSON
无输出内容。
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2423 ms Tokens:122 时间:2026-08-29 17:43:48
JSON
{"status":"ok","message":"stable"}
#39 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2751 ms Tokens:136 时间:2026-08-29 17:43:47
JSON
{"status":"ok","message":"stable"}
#40 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:212 ms Tokens:- 时间:2026-08-29 17:43:50
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:192 ms Tokens:- 时间:2026-08-29 17:43:50
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:207 ms Tokens:- 时间:2026-08-29 17:43:50
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:4987 ms Tokens:153 时间:2026-08-29 17:43:51
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:5327 ms Tokens:177 时间:2026-08-29 17:43:50
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:4821 ms Tokens:159 时间:2026-08-29 17:43:56
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 1129 200 113
DeepSeek-v4-pro-01 成功 1323 200 113
DeepSeek-v4-pro-01 成功 1222 200 113
DeepSeek-v4-pro-03 成功 1136 200 113
DeepSeek-v4-pro-03 成功 1233 200 113
DeepSeek-v4-pro-03 成功 1237 200 113
DeepSeek-v4-pro-04 成功 1179 200 113
DeepSeek-v4-pro-04 成功 1154 200 113
DeepSeek-v4-pro-04 成功 714 200 113
DeepSeek-v4-pro-02 成功 843 200 113
DeepSeek-v4-pro-02 成功 1048 200 113
DeepSeek-v4-pro-02 成功 1234 200 113
jd-gemini-3.1-pro-preview 成功 11029 200 26
jd-gemini-3.1-pro-preview 成功 3750 200 27
腾讯 Gemini 3.5 Flash 成功 4109 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 4678 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 4226 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
jd-gemini-3.1-pro-preview 失败 30255 - - timeout: The read operation timed out
qwen3.6-plus 成功 4152 200 222 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 3640 200 202 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 588 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 486 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 7225 200 389 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 547 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 442 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 492 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 484 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 2282 200 115
Kimi K3 - Aliyun Bailian 成功 2607 200 115
Kimi K3 - Aliyun Bailian 成功 3466 200 115
Kimi K3 成功 6141 200 187 {"status":"ok","message":"stable"}
Kimi K3 成功 4724 200 185 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2439 200 115 {"status":"ok","
Kimi K3 成功 5495 200 225 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1967 200 115
Kimi K3 - TopenRouter 成功 2040 200 115 {"status":"ok","message":"stable
Qwen3.8-Max 成功 1408 200 81
Qwen3.8-Max 成功 2423 200 122 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2751 200 136 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 212 400 - 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
MiniMax H3 Context IR 失败 207 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 4987 200 153 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5327 200 177 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4821 200 159 {"status":"ok","message":"stable"}