Model Channel Lab

测试结果

Run ID: 20260830-231404-f4caec9c

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟2915 ms

P95 / Tokens5423 / 4527

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	1162	1195	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1195	1291	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1316	1542	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1417	1905	339
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1783	2147	345
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	1798	1933	382
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2195	2411	345
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	3604	4168	600
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	可用	3690	5423	316
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4506	4827	78
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	6028	7653	614
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	6284	8553	491
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：1508 ms Tokens：113 时间：2026-08-30 23:13:06

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1542 ms Tokens：113 时间：2026-08-30 23:13:06

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：900 ms Tokens：113 时间：2026-08-30 23:13:07

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1201 ms Tokens：113 时间：2026-08-30 23:13:07

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1147 ms Tokens：113 时间：2026-08-30 23:13:08

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1905 ms Tokens：113 时间：2026-08-30 23:13:08

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1188 ms Tokens：113 时间：2026-08-30 23:13:09

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1107 ms Tokens：113 时间：2026-08-30 23:13:10

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1291 ms Tokens：113 时间：2026-08-30 23:13:11

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1176 ms Tokens：113 时间：2026-08-30 23:13:11

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1195 ms Tokens：113 时间：2026-08-30 23:13:12

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1115 ms Tokens：113 时间：2026-08-30 23:13:12

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：2886 ms Tokens：26 时间：2026-08-30 23:13:13

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：2761 ms Tokens：26 时间：2026-08-30 23:13:13

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：4827 ms Tokens：26 时间：2026-08-30 23:13:16

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

模型：gemini-3.1-pro-preview 延迟：5423 ms Tokens：264 时间：2026-08-30 23:13:16

JSON

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

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4422 ms Tokens：26 时间：2026-08-30 23:13:21

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4269 ms Tokens：26 时间：2026-08-30 23:13:21

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3338 ms Tokens：189 时间：2026-08-30 23:13:25

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3307 ms Tokens：189 时间：2026-08-30 23:13:26

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：560 ms Tokens：- 时间：2026-08-30 23:13:29

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：493 ms Tokens：- 时间：2026-08-30 23:13:30

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：544 ms Tokens：- 时间：2026-08-30 23:13:30

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：457 ms Tokens：- 时间：2026-08-30 23:13:31

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：508 ms Tokens：- 时间：2026-08-30 23:13:31

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：442 ms Tokens：- 时间：2026-08-30 23:13:32

JSON

HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}

#27 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4168 ms Tokens：222 时间：2026-08-30 23:13:29

JSON

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

#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1062 ms Tokens：115 时间：2026-08-30 23:13:33

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2140 ms Tokens：115 时间：2026-08-30 23:13:32

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2147 ms Tokens：115 时间：2026-08-30 23:13:34

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5267 ms Tokens：220 时间：2026-08-30 23:13:36

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：7653 ms Tokens：205 时间：2026-08-30 23:13:34

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2411 ms Tokens：115 时间：2026-08-30 23:13:42

JSON

无输出内容。

#34 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5164 ms Tokens：189 时间：2026-08-30 23:13:41

JSON

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

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2309 ms Tokens：115 时间：2026-08-30 23:13:44

JSON

{"status":"ok","

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1658 ms Tokens：128 时间：2026-08-30 23:13:47

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1865 ms Tokens：115 时间：2026-08-30 23:13:46

JSON

{"status

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1805 ms Tokens：126 时间：2026-08-30 23:13:48

JSON

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

#39 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1933 ms Tokens：128 时间：2026-08-30 23:13:48

JSON

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

#40 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：199 ms Tokens：- 时间：2026-08-30 23:13:50

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：224 ms Tokens：- 时间：2026-08-30 23:13:50

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：200 ms Tokens：- 时间：2026-08-30 23:13:50

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：5134 ms Tokens：169 时间：2026-08-30 23:13:50

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：5167 ms Tokens：169 时间：2026-08-30 23:13:51

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：8553 ms Tokens：153 时间：2026-08-30 23:13:55

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	1508	200	113
DeepSeek-v4-pro-01	成功	1542	200	113
DeepSeek-v4-pro-01	成功	900	200	113
DeepSeek-v4-pro-03	成功	1201	200	113
DeepSeek-v4-pro-03	成功	1147	200	113
DeepSeek-v4-pro-03	成功	1905	200	113
DeepSeek-v4-pro-04	成功	1188	200	113
DeepSeek-v4-pro-04	成功	1107	200	113
DeepSeek-v4-pro-04	成功	1291	200	113
DeepSeek-v4-pro-02	成功	1176	200	113
DeepSeek-v4-pro-02	成功	1195	200	113
DeepSeek-v4-pro-02	成功	1115	200	113
jd-gemini-3.1-pro-preview	成功	2886	200	26
jd-gemini-3.1-pro-preview	成功	2761	200	26
腾讯 Gemini 3.5 Flash	成功	4827	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	5423	200	264	{"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash	成功	4422	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	4269	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	3338	200	189	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3307	200	189	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	560	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	493	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	544	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	457	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	508	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"}
qwen3.6-plus	成功	4168	200	222	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	1062	200	115
Kimi K3 - Aliyun Bailian	成功	2140	200	115
Kimi K3 - Aliyun Bailian	成功	2147	200	115
Kimi K3	成功	5267	200	220	{"status":"ok","message":"stable"}
Kimi K3	成功	7653	200	205	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2411	200	115
Kimi K3	成功	5164	200	189	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2309	200	115	{"status":"ok","
Qwen3.8-Max	成功	1658	200	128	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1865	200	115	{"status
Qwen3.8-Max	成功	1805	200	126	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1933	200	128	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	199	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	224	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	200	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	5134	200	169	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5167	200	169	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	8553	200	153	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细