Model Channel Lab

测试结果

Run ID: 20260831-001520-432e0d8f

导出 JSON

总请求45

成功 / 失败35/10

成功率77.78%

平均延迟3268 ms

P95 / Tokens6983 / 4455

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	930	1257	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1059	1114	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1124	1301	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1369	1994	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	1651	1676	377
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2236	2636	345
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2342	2704	345
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	4415	5679	745
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4459	4499	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5651	6347	578
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	6241	6983	579
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	2/3	1/3	66.67%	33.33%	不稳定	9975	11640	52	timeout: The read operation timed out
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：1011 ms Tokens：113 时间：2026-08-31 00:14:04

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1104 ms Tokens：113 时间：2026-08-31 00:14:04

JSON

无输出内容。

#3 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1257 ms Tokens：113 时间：2026-08-31 00:14:05

JSON

无输出内容。

#4 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1994 ms Tokens：113 时间：2026-08-31 00:14:05

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：812 ms Tokens：113 时间：2026-08-31 00:14:07

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：722 ms Tokens：113 时间：2026-08-31 00:14:07

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1301 ms Tokens：113 时间：2026-08-31 00:14:07

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1022 ms Tokens：113 时间：2026-08-31 00:14:08

JSON

{"status

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1050 ms Tokens：113 时间：2026-08-31 00:14:09

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1003 ms Tokens：113 时间：2026-08-31 00:14:09

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1060 ms Tokens：113 时间：2026-08-31 00:14:10

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1114 ms Tokens：113 时间：2026-08-31 00:14:10

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：8311 ms Tokens：26 时间：2026-08-31 00:14:11

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：11640 ms Tokens：26 时间：2026-08-31 00:14:19

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：4419 ms Tokens：26 时间：2026-08-31 00:14:31

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：4460 ms Tokens：26 时间：2026-08-31 00:14:35

JSON

#17 jd-gemini-3.1-pro-preview 失败 HTTP -

模型：gemini-3.1-pro-preview 延迟：30196 ms Tokens：- 时间：2026-08-31 00:14:11

JSON

timeout: The read operation timed out

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4499 ms Tokens：26 时间：2026-08-31 00:14:40

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3944 ms Tokens：219 时间：2026-08-31 00:14:41

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3622 ms Tokens：202 时间：2026-08-31 00:14:44

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：521 ms Tokens：- 时间：2026-08-31 00:14:48

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：2026-08-31 00:14:48

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：422 ms Tokens：- 时间：2026-08-31 00:14:49

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：516 ms Tokens：- 时间：2026-08-31 00:14:49

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：441 ms Tokens：- 时间：2026-08-31 00:14:50

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：551 ms Tokens：- 时间：2026-08-31 00:14:50

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：5679 ms Tokens：324 时间：2026-08-31 00:14:45

JSON

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

#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1948 ms Tokens：115 时间：2026-08-31 00:14:51

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2636 ms Tokens：115 时间：2026-08-31 00:14:51

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2125 ms Tokens：115 时间：2026-08-31 00:14:53

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6983 ms Tokens：184 时间：2026-08-31 00:14:53

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5960 ms Tokens：188 时间：2026-08-31 00:14:55

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2704 ms Tokens：115 时间：2026-08-31 00:15:01

JSON

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2350 ms Tokens：115 时间：2026-08-31 00:15:04

JSON

{"status":"ok","

#35 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5781 ms Tokens：207 时间：2026-08-31 00:15:00

JSON

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

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1676 ms Tokens：126 时间：2026-08-31 00:15:06

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1974 ms Tokens：115 时间：2026-08-31 00:15:06

JSON

{"status":"ok","message

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1629 ms Tokens：126 时间：2026-08-31 00:15:08

JSON

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

#39 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1648 ms Tokens：125 时间：2026-08-31 00:15:08

JSON

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

#40 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：211 ms Tokens：- 时间：2026-08-31 00:15:10

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：2026-08-31 00:15:10

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：255 ms Tokens：- 时间：2026-08-31 00:15:10

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：6106 ms Tokens：221 时间：2026-08-31 00:15:10

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：6347 ms Tokens：196 时间：2026-08-31 00:15:10

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：4500 ms Tokens：161 时间：2026-08-31 00:15:16

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	1011	200	113
DeepSeek-v4-pro-01	成功	1104	200	113
DeepSeek-v4-pro-03	成功	1257	200	113
DeepSeek-v4-pro-01	成功	1994	200	113
DeepSeek-v4-pro-03	成功	812	200	113
DeepSeek-v4-pro-03	成功	722	200	113
DeepSeek-v4-pro-04	成功	1301	200	113
DeepSeek-v4-pro-04	成功	1022	200	113	{"status
DeepSeek-v4-pro-04	成功	1050	200	113
DeepSeek-v4-pro-02	成功	1003	200	113
DeepSeek-v4-pro-02	成功	1060	200	113
DeepSeek-v4-pro-02	成功	1114	200	113
jd-gemini-3.1-pro-preview	成功	8311	200	26
jd-gemini-3.1-pro-preview	成功	11640	200	26
腾讯 Gemini 3.5 Flash	成功	4419	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	4460	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	失败	30196	-	-	timeout: The read operation timed out
腾讯 Gemini 3.5 Flash	成功	4499	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	3944	200	219	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3622	200	202	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	521	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	422	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	516	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	441	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	551	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	5679	200	324	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	1948	200	115
Kimi K3 - Aliyun Bailian	成功	2636	200	115
Kimi K3 - Aliyun Bailian	成功	2125	200	115
Kimi K3	成功	6983	200	184	{"status":"ok","message":"stable"}
Kimi K3	成功	5960	200	188	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2704	200	115	{"
Kimi K3 - TopenRouter	成功	2350	200	115	{"status":"ok","
Kimi K3	成功	5781	200	207	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1676	200	126	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1974	200	115	{"status":"ok","message
Qwen3.8-Max	成功	1629	200	126	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1648	200	125	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	211	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
MiniMax H3 Context IR	失败	255	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	6106	200	221	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6347	200	196	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4500	200	161	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细