Model Channel Lab

测试结果

Run ID: 20260831-011619-0efbc545

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3034 ms

P95 / Tokens6054 / 4425

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	994	1116	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1031	1053	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1176	1226	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1195	1221	339
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1866	1924	345
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2475	2669	345
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2555	3215	392
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	3639	4298	79
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	4390	4729	750
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4521	4729	78
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	5824	6193	586
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	6743	10284	494
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：996 ms Tokens：113 时间：2026-08-31 01:15:21

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1044 ms Tokens：113 时间：2026-08-31 01:15:21

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1053 ms Tokens：113 时间：2026-08-31 01:15:22

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1226 ms Tokens：113 时间：2026-08-31 01:15:22

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1162 ms Tokens：113 时间：2026-08-31 01:15:23

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1142 ms Tokens：113 时间：2026-08-31 01:15:23

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1019 ms Tokens：113 时间：2026-08-31 01:15:24

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1116 ms Tokens：113 时间：2026-08-31 01:15:24

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：848 ms Tokens：113 时间：2026-08-31 01:15:25

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1161 ms Tokens：113 时间：2026-08-31 01:15:25

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1221 ms Tokens：113 时间：2026-08-31 01:15:26

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1204 ms Tokens：113 时间：2026-08-31 01:15:26

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：3158 ms Tokens：26 时间：2026-08-31 01:15:27

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：4298 ms Tokens：26 时间：2026-08-31 01:15:28

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：3461 ms Tokens：27 时间：2026-08-31 01:15:30

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：4344 ms Tokens：26 时间：2026-08-31 01:15:32

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：4490 ms Tokens：26 时间：2026-08-31 01:15:34

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4729 ms Tokens：26 时间：2026-08-31 01:15:36

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4583 ms Tokens：264 时间：2026-08-31 01:15:38

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4729 ms Tokens：264 时间：2026-08-31 01:15:41

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：636 ms Tokens：- 时间：2026-08-31 01:15:46

JSON

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

#22 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3859 ms Tokens：222 时间：2026-08-31 01:15:43

JSON

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

#23 pixflow-gemini-3.1-pro-preview 失败 HTTP 403

模型：gemini-3.1-pro-preview 延迟：692 ms Tokens：- 时间：2026-08-31 01:15:46

JSON

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

#24 pixflow-gemini-3.1-pro-preview 失败 HTTP 403

模型：gemini-3.1-pro-preview 延迟：515 ms Tokens：- 时间：2026-08-31 01:15:47

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：526 ms Tokens：- 时间：2026-08-31 01:15:47

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：604 ms Tokens：- 时间：2026-08-31 01:15:47

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：544 ms Tokens：- 时间：2026-08-31 01:15:48

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：1874 ms Tokens：115 时间：2026-08-31 01:15:48

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1801 ms Tokens：115 时间：2026-08-31 01:15:48

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1924 ms Tokens：115 时间：2026-08-31 01:15:50

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6193 ms Tokens：189 时间：2026-08-31 01:15:50

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6054 ms Tokens：199 时间：2026-08-31 01:15:51

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2669 ms Tokens：115 时间：2026-08-31 01:15:58

JSON

无输出内容。

#34 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5226 ms Tokens：198 时间：2026-08-31 01:15:56

JSON

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

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2644 ms Tokens：115 时间：2026-08-31 01:16:00

JSON

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2113 ms Tokens：115 时间：2026-08-31 01:16:01

JSON

{"status":"ok","

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2279 ms Tokens：124 时间：2026-08-31 01:16:03

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2172 ms Tokens：135 时间：2026-08-31 01:16:04

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：1261 ms Tokens：- 时间：2026-08-31 01:16:06

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：191 ms Tokens：- 时间：2026-08-31 01:16:07

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：615 ms Tokens：- 时间：2026-08-31 01:16:07

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：3215 ms Tokens：133 时间：2026-08-31 01:16:05

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：5387 ms Tokens：146 时间：2026-08-31 01:16:08

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：4559 ms Tokens：178 时间：2026-08-31 01:16:13

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：10284 ms Tokens：170 时间：2026-08-31 01:16:08

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	996	200	113
DeepSeek-v4-pro-01	成功	1044	200	113
DeepSeek-v4-pro-01	成功	1053	200	113
DeepSeek-v4-pro-03	成功	1226	200	113
DeepSeek-v4-pro-03	成功	1162	200	113
DeepSeek-v4-pro-03	成功	1142	200	113
DeepSeek-v4-pro-04	成功	1019	200	113
DeepSeek-v4-pro-04	成功	1116	200	113
DeepSeek-v4-pro-04	成功	848	200	113
DeepSeek-v4-pro-02	成功	1161	200	113
DeepSeek-v4-pro-02	成功	1221	200	113
DeepSeek-v4-pro-02	成功	1204	200	113
jd-gemini-3.1-pro-preview	成功	3158	200	26
jd-gemini-3.1-pro-preview	成功	4298	200	26
jd-gemini-3.1-pro-preview	成功	3461	200	27
腾讯 Gemini 3.5 Flash	成功	4344	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	4490	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	4729	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	4583	200	264	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4729	200	264	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	636	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	3859	200	222	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	692	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"}
yuling-gpt-5.5	失败	526	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	604	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	544	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	1874	200	115
Kimi K3 - Aliyun Bailian	成功	1801	200	115
Kimi K3 - Aliyun Bailian	成功	1924	200	115
Kimi K3	成功	6193	200	189	{"status":"ok","message":"stable"}
Kimi K3	成功	6054	200	199	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2669	200	115
Kimi K3	成功	5226	200	198	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2644	200	115	{"
Kimi K3 - TopenRouter	成功	2113	200	115	{"status":"ok","
Qwen3.8-Max	成功	2279	200	124	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2172	200	135	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	1261	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	191	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	615	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	3215	200	133	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5387	200	146	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4559	200	178	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	10284	200	170	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细