Model Channel Lab

测试结果

Run ID: 20260830-065739-83e23066

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟2793 ms

P95 / Tokens6510 / 4891

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-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1049	1367	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1076	1131	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1159	1444	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1184	1673	459
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1190	1363	339
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1519	2061	345
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2200	2343	393
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2819	3050	78
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4347	4588	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	稳定	4556	4904	506
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5996	10585	1041
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	6423	6996	635
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：1048 ms Tokens：113 时间：2026-08-30 06:56:45

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1051 ms Tokens：113 时间：2026-08-30 06:56:45

JSON

无输出内容。

#3 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1087 ms Tokens：113 时间：2026-08-30 06:56:46

JSON

无输出内容。

#4 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1131 ms Tokens：113 时间：2026-08-30 06:56:46

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：947 ms Tokens：113 时间：2026-08-30 06:56:47

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1444 ms Tokens：113 时间：2026-08-30 06:56:47

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1367 ms Tokens：113 时间：2026-08-30 06:56:48

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1018 ms Tokens：113 时间：2026-08-30 06:56:49

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：764 ms Tokens：113 时间：2026-08-30 06:56:49

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1168 ms Tokens：113 时间：2026-08-30 06:56:50

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1041 ms Tokens：113 时间：2026-08-30 06:56:50

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1363 ms Tokens：113 时间：2026-08-30 06:56:51

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：2753 ms Tokens：26 时间：2026-08-30 06:56:51

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：2654 ms Tokens：26 时间：2026-08-30 06:56:52

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：3050 ms Tokens：26 时间：2026-08-30 06:56:54

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：4588 ms Tokens：26 时间：2026-08-30 06:56:55

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

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4337 ms Tokens：26 时间：2026-08-30 06:56:57

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4117 ms Tokens：26 时间：2026-08-30 06:56:59

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3526 ms Tokens：202 时间：2026-08-30 06:57:01

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3877 ms Tokens：222 时间：2026-08-30 06:57:05

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：531 ms Tokens：- 时间：2026-08-30 06:57:09

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：515 ms Tokens：- 时间：2026-08-30 06:57:09

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：491 ms Tokens：- 时间：2026-08-30 06:57:10

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：482 ms Tokens：- 时间：2026-08-30 06:57:10

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：530 ms Tokens：- 时间：2026-08-30 06:57:11

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：527 ms Tokens：- 时间：2026-08-30 06:57:11

JSON

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

#27 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1151 ms Tokens：115 时间：2026-08-30 06:57:12

JSON

无输出内容。

#28 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：10585 ms Tokens：617 时间：2026-08-30 06:57:04

JSON

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

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1345 ms Tokens：115 时间：2026-08-30 06:57:13

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2061 ms Tokens：115 时间：2026-08-30 06:57:14

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6996 ms Tokens：201 时间：2026-08-30 06:57:14

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5765 ms Tokens：228 时间：2026-08-30 06:57:16

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1673 ms Tokens：153 时间：2026-08-30 06:57:22

JSON

无输出内容。

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：911 ms Tokens：153 时间：2026-08-30 06:57:24

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：969 ms Tokens：153 时间：2026-08-30 06:57:25

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2343 ms Tokens：138 时间：2026-08-30 06:57:25

JSON

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

#37 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6510 ms Tokens：206 时间：2026-08-30 06:57:21

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2148 ms Tokens：128 时间：2026-08-30 06:57:28

JSON

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

#39 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2110 ms Tokens：127 时间：2026-08-30 06:57:28

JSON

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

#40 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：213 ms Tokens：- 时间：2026-08-30 06:57:30

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：232 ms Tokens：- 时间：2026-08-30 06:57:30

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：283 ms Tokens：- 时间：2026-08-30 06:57:30

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：4904 ms Tokens：188 时间：2026-08-30 06:57:30

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：4663 ms Tokens：174 时间：2026-08-30 06:57:30

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：4102 ms Tokens：144 时间：2026-08-30 06:57:35

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	1048	200	113
DeepSeek-v4-pro-01	成功	1051	200	113
DeepSeek-v4-pro-03	成功	1087	200	113
DeepSeek-v4-pro-01	成功	1131	200	113
DeepSeek-v4-pro-03	成功	947	200	113
DeepSeek-v4-pro-03	成功	1444	200	113
DeepSeek-v4-pro-04	成功	1367	200	113
DeepSeek-v4-pro-04	成功	1018	200	113
DeepSeek-v4-pro-04	成功	764	200	113
DeepSeek-v4-pro-02	成功	1168	200	113
DeepSeek-v4-pro-02	成功	1041	200	113
DeepSeek-v4-pro-02	成功	1363	200	113
jd-gemini-3.1-pro-preview	成功	2753	200	26
jd-gemini-3.1-pro-preview	成功	2654	200	26
jd-gemini-3.1-pro-preview	成功	3050	200	26
腾讯 Gemini 3.5 Flash	成功	4588	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	4337	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	4117	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	3526	200	202	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3877	200	222	{"status":"ok","message":"stable"}
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	515	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	491	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	482	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	530	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	527	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	1151	200	115
qwen3.6-plus	成功	10585	200	617	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	1345	200	115
Kimi K3 - Aliyun Bailian	成功	2061	200	115
Kimi K3	成功	6996	200	201	{"status":"ok","message":"stable"}
Kimi K3	成功	5765	200	228	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1673	200	153
Kimi K3 - TopenRouter	成功	911	200	153
Kimi K3 - TopenRouter	成功	969	200	153
Qwen3.8-Max	成功	2343	200	138	{"status":"ok","message":"stable"}
Kimi K3	成功	6510	200	206	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2148	200	128	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2110	200	127	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	213	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	232	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	283	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	4904	200	188	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4663	200	174	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4102	200	144	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细