Model Channel Lab

测试结果

Run ID: 20260830-025404-a1c4917a

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3220 ms

P95 / Tokens5977 / 4579

渠道	模型	成功	失败	成功率	失败率	稳定性	平均延迟 ms	P95 ms	Tokens	首个错误
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	982	1423	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1080	1173	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1117	1197	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1125	1211	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1244	1739	459
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2950	3665	380
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2953	3713	345
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	4183	4700	345
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4252	4323	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	4537	5204	505
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5992	8065	1032
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	可用	8222	20046	79
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：1081 ms Tokens：113 时间：2026-08-30 02:53:02

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1084 ms Tokens：113 时间：2026-08-30 02:53:02

JSON

无输出内容。

#3 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1169 ms Tokens：113 时间：2026-08-30 02:53:03

JSON

无输出内容。

#4 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1211 ms Tokens：113 时间：2026-08-30 02:53:03

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：987 ms Tokens：113 时间：2026-08-30 02:53:05

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1197 ms Tokens：113 时间：2026-08-30 02:53:05

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：919 ms Tokens：113 时间：2026-08-30 02:53:06

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1149 ms Tokens：113 时间：2026-08-30 02:53:06

JSON

无输出内容。

#9 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：731 ms Tokens：113 时间：2026-08-30 02:53:07

JSON

无输出内容。

#10 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1173 ms Tokens：113 时间：2026-08-30 02:53:07

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：794 ms Tokens：113 时间：2026-08-30 02:53:08

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1423 ms Tokens：113 时间：2026-08-30 02:53:08

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：2373 ms Tokens：26 时间：2026-08-30 02:53:08

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：2248 ms Tokens：26 时间：2026-08-30 02:53:11

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：4323 ms Tokens：26 时间：2026-08-30 02:53:13

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：4171 ms Tokens：26 时间：2026-08-30 02:53:17

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4264 ms Tokens：26 时间：2026-08-30 02:53:22

JSON

#18 jd-gemini-3.1-pro-preview 成功 HTTP 200

模型：gemini-3.1-pro-preview 延迟：20046 ms Tokens：27 时间：2026-08-30 02:53:09

JSON

无输出内容。

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：8065 ms Tokens：466 时间：2026-08-30 02:53:26

JSON

{"status":"ok","message":"stable"}

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5977 ms Tokens：344 时间：2026-08-30 02:53:29

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：530 ms Tokens：- 时间：2026-08-30 02:53:35

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：531 ms Tokens：- 时间：2026-08-30 02:53:36

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：516 ms Tokens：- 时间：2026-08-30 02:53:36

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：537 ms Tokens：- 时间：2026-08-30 02:53:37

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：496 ms Tokens：- 时间：2026-08-30 02:53:37

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：3935 ms Tokens：222 时间：2026-08-30 02:53:34

JSON

{"status":"ok","message":"stable"}

#27 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：444 ms Tokens：- 时间：2026-08-30 02:53:38

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：2735 ms Tokens：115 时间：2026-08-30 02:53:38

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2411 ms Tokens：115 时间：2026-08-30 02:53:38

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：3713 ms Tokens：115 时间：2026-08-30 02:53:41

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4700 ms Tokens：115 时间：2026-08-30 02:53:41

JSON

{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4058 ms Tokens：115 时间：2026-08-30 02:53:44

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 成功 HTTP 200

模型：kimi-k3 延迟：3793 ms Tokens：115 时间：2026-08-30 02:53:45

JSON

{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1739 ms Tokens：153 时间：2026-08-30 02:53:48

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：992 ms Tokens：153 时间：2026-08-30 02:53:49

JSON

无输出内容。

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1001 ms Tokens：153 时间：2026-08-30 02:53:50

JSON

无输出内容。

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：3665 ms Tokens：127 时间：2026-08-30 02:53:50

JSON

{"status":"ok","message":"stable"}

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2947 ms Tokens：128 时间：2026-08-30 02:53:51

JSON

{"status":"ok","message":"stable"}

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：176 ms Tokens：- 时间：2026-08-30 02:53:54

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：2026-08-30 02:53:54

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：234 ms Tokens：- 时间：2026-08-30 02:53:54

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：2238 ms Tokens：125 时间：2026-08-30 02:53:54

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：5204 ms Tokens：188 时间：2026-08-30 02:53:55

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：4122 ms Tokens：166 时间：2026-08-30 02:53:56

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：4286 ms Tokens：151 时间：2026-08-30 02:54:00

JSON

{"status":"ok","message":"stable"}

表格明细

渠道	状态	延迟 ms	HTTP	Tokens	输出 / 错误
DeepSeek-v4-pro-01	成功	1081	200	113
DeepSeek-v4-pro-01	成功	1084	200	113
DeepSeek-v4-pro-03	成功	1169	200	113
DeepSeek-v4-pro-01	成功	1211	200	113
DeepSeek-v4-pro-03	成功	987	200	113
DeepSeek-v4-pro-03	成功	1197	200	113
DeepSeek-v4-pro-04	成功	919	200	113
DeepSeek-v4-pro-04	成功	1149	200	113
DeepSeek-v4-pro-02	成功	731	200	113
DeepSeek-v4-pro-04	成功	1173	200	113
DeepSeek-v4-pro-02	成功	794	200	113
DeepSeek-v4-pro-02	成功	1423	200	113
jd-gemini-3.1-pro-preview	成功	2373	200	26
jd-gemini-3.1-pro-preview	成功	2248	200	26
腾讯 Gemini 3.5 Flash	成功	4323	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	4171	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	4264	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	成功	20046	200	27
qwen3.6-plus	成功	8065	200	466	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	5977	200	344	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	530	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	531	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	516	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	537	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	496	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	3935	200	222	{"status":"ok","message":"stable"}
yuling-gpt-5.5	失败	444	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2735	200	115
Kimi K3 - Aliyun Bailian	成功	2411	200	115
Kimi K3 - Aliyun Bailian	成功	3713	200	115
Kimi K3	成功	4700	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	4058	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	3793	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	1739	200	153
Kimi K3 - TopenRouter	成功	992	200	153
Kimi K3 - TopenRouter	成功	1001	200	153
Qwen3.8-Max	成功	3665	200	127	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2947	200	128	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	176	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	234	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2238	200	125	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5204	200	188	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4122	200	166	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4286	200	151	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细