Model Channel Lab

测试结果

Run ID: 20260829-204725-b9337ddb

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3236 ms

P95 / Tokens7107 / 4445

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-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1032	1081	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1087	1311	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1114	1180	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1269	1383	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2143	2238	392
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2271	2682	345
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2388	2711	345
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2872	3082	78
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4099	4120	78
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5162	7107	865
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5733	6234	477
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	9669	12211	509
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：1336 ms Tokens：113 时间：2026-08-29 20:46:22

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1383 ms Tokens：113 时间：2026-08-29 20:46:22

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1090 ms Tokens：113 时间：2026-08-29 20:46:23

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1081 ms Tokens：113 时间：2026-08-29 20:46:23

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1004 ms Tokens：113 时间：2026-08-29 20:46:24

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1013 ms Tokens：113 时间：2026-08-29 20:46:24

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1065 ms Tokens：113 时间：2026-08-29 20:46:25

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1180 ms Tokens：113 时间：2026-08-29 20:46:25

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1097 ms Tokens：113 时间：2026-08-29 20:46:26

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1092 ms Tokens：113 时间：2026-08-29 20:46:27

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：860 ms Tokens：113 时间：2026-08-29 20:46:28

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1311 ms Tokens：113 时间：2026-08-29 20:46:28

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：2612 ms Tokens：26 时间：2026-08-29 20:46:28

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：3082 ms Tokens：26 时间：2026-08-29 20:46:29

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：2923 ms Tokens：26 时间：2026-08-29 20:46:31

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：4119 ms Tokens：26 时间：2026-08-29 20:46:32

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：4120 ms Tokens：26 时间：2026-08-29 20:46:34

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4060 ms Tokens：26 时间：2026-08-29 20:46:36

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3422 ms Tokens：189 时间：2026-08-29 20:46:38

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4957 ms Tokens：266 时间：2026-08-29 20:46:40

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：527 ms Tokens：- 时间：2026-08-29 20:46:45

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：527 ms Tokens：- 时间：2026-08-29 20:46:46

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：526 ms Tokens：- 时间：2026-08-29 20:46:46

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：461 ms Tokens：- 时间：2026-08-29 20:46:47

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：498 ms Tokens：- 时间：2026-08-29 20:46:47

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：484 ms Tokens：- 时间：2026-08-29 20:46:48

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：7107 ms Tokens：410 时间：2026-08-29 20:46:42

JSON

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

#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2711 ms Tokens：115 时间：2026-08-29 20:46:48

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2181 ms Tokens：115 时间：2026-08-29 20:46:49

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2272 ms Tokens：115 时间：2026-08-29 20:46:51

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：9845 ms Tokens：196 时间：2026-08-29 20:46:53

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：12211 ms Tokens：198 时间：2026-08-29 20:46:51

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1612 ms Tokens：115 时间：2026-08-29 20:47:03

JSON

无输出内容。

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2682 ms Tokens：115 时间：2026-08-29 20:47:05

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2521 ms Tokens：115 时间：2026-08-29 20:47:07

JSON

#36 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6953 ms Tokens：115 时间：2026-08-29 20:47:03

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"}

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2085 ms Tokens：129 时间：2026-08-29 20:47:10

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2238 ms Tokens：136 时间：2026-08-29 20:47:10

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：190 ms Tokens：- 时间：2026-08-29 20:47:12

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：201 ms Tokens：- 时间：2026-08-29 20:47:12

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：151 ms Tokens：- 时间：2026-08-29 20:47:12

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：2106 ms Tokens：127 时间：2026-08-29 20:47:12

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：5694 ms Tokens：160 时间：2026-08-29 20:47:13

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：5271 ms Tokens：177 时间：2026-08-29 20:47:14

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：6234 ms Tokens：140 时间：2026-08-29 20:47:18

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	1336	200	113
DeepSeek-v4-pro-01	成功	1383	200	113
DeepSeek-v4-pro-01	成功	1090	200	113
DeepSeek-v4-pro-03	成功	1081	200	113
DeepSeek-v4-pro-03	成功	1004	200	113
DeepSeek-v4-pro-03	成功	1013	200	113
DeepSeek-v4-pro-04	成功	1065	200	113
DeepSeek-v4-pro-04	成功	1180	200	113
DeepSeek-v4-pro-04	成功	1097	200	113
DeepSeek-v4-pro-02	成功	1092	200	113
DeepSeek-v4-pro-02	成功	860	200	113
DeepSeek-v4-pro-02	成功	1311	200	113
jd-gemini-3.1-pro-preview	成功	2612	200	26
jd-gemini-3.1-pro-preview	成功	3082	200	26
jd-gemini-3.1-pro-preview	成功	2923	200	26
腾讯 Gemini 3.5 Flash	成功	4119	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	4120	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	4060	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	3422	200	189	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4957	200	266	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	527	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	527	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	526	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	461	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	498	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"}
qwen3.6-plus	成功	7107	200	410	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	2711	200	115
Kimi K3 - Aliyun Bailian	成功	2181	200	115
Kimi K3 - Aliyun Bailian	成功	2272	200	115
Kimi K3	成功	9845	200	196	{"status":"ok","message":"stable"}
Kimi K3	成功	12211	200	198	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1612	200	115
Kimi K3 - TopenRouter	成功	2682	200	115
Kimi K3 - TopenRouter	成功	2521	200	115	{"
Kimi K3	成功	6953	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"}
Qwen3.8-Max	成功	2085	200	129	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2238	200	136	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	190	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	201	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	151	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2106	200	127	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5694	200	160	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5271	200	177	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6234	200	140	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细