Model Channel Lab

测试结果

Run ID: 20260830-160654-fb19bd77

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟2992 ms

P95 / Tokens5661 / 4552

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-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1206	1518	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1305	1486	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1381	1611	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	1653	1743	377
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1658	2403	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2623	3019	345
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2707	3554	345
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	3512	4861	79
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4292	4367	78
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	5089	5661	567
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5176	5710	514
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5298	8876	891
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：1038 ms Tokens：113 时间：2026-08-30 16:05:56

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1063 ms Tokens：113 时间：2026-08-30 16:05:56

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1518 ms Tokens：113 时间：2026-08-30 16:05:57

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：2403 ms Tokens：113 时间：2026-08-30 16:05:57

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1420 ms Tokens：113 时间：2026-08-30 16:05:58

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1151 ms Tokens：113 时间：2026-08-30 16:05:59

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1486 ms Tokens：113 时间：2026-08-30 16:06:00

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1029 ms Tokens：113 时间：2026-08-30 16:06:00

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1402 ms Tokens：113 时间：2026-08-30 16:06:01

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1611 ms Tokens：113 时间：2026-08-30 16:06:01

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1007 ms Tokens：113 时间：2026-08-30 16:06:03

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1527 ms Tokens：113 时间：2026-08-30 16:06:03

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：2551 ms Tokens：26 时间：2026-08-30 16:06:04

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：3124 ms Tokens：27 时间：2026-08-30 16:06:05

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：4861 ms Tokens：26 时间：2026-08-30 16:06:06

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：4367 ms Tokens：26 时间：2026-08-30 16:06:08

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：4210 ms Tokens：26 时间：2026-08-30 16:06:11

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4301 ms Tokens：26 时间：2026-08-30 16:06:12

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3256 ms Tokens：189 时间：2026-08-30 16:06:16

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3763 ms Tokens：213 时间：2026-08-30 16:06:20

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：524 ms Tokens：- 时间：2026-08-30 16:06:23

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：8876 ms Tokens：489 时间：2026-08-30 16:06:15

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：666 ms Tokens：- 时间：2026-08-30 16:06:24

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：543 ms Tokens：- 时间：2026-08-30 16:06:24

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：541 ms Tokens：- 时间：2026-08-30 16:06:25

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：461 ms Tokens：- 时间：2026-08-30 16:06:25

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：466 ms Tokens：- 时间：2026-08-30 16:06:25

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：2473 ms Tokens：115 时间：2026-08-30 16:06:25

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2096 ms Tokens：115 时间：2026-08-30 16:06:26

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：3554 ms Tokens：115 时间：2026-08-30 16:06:28

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4905 ms Tokens：189 时间：2026-08-30 16:06:28

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5661 ms Tokens：192 时间：2026-08-30 16:06:31

JSON

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

#33 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4702 ms Tokens：186 时间：2026-08-30 16:06:33

JSON

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

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2340 ms Tokens：115 时间：2026-08-30 16:06:37

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3019 ms Tokens：115 时间：2026-08-30 16:06:37

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1611 ms Tokens：125 时间：2026-08-30 16:06:40

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2511 ms Tokens：115 时间：2026-08-30 16:06:40

JSON

无输出内容。

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1743 ms Tokens：127 时间：2026-08-30 16:06:42

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：214 ms Tokens：- 时间：2026-08-30 16:06:43

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：158 ms Tokens：- 时间：2026-08-30 16:06:43

JSON

HTTP 400: binding: expr_path=content, cause=missing required parameter

#41 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1606 ms Tokens：125 时间：2026-08-30 16:06:42

JSON

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

#42 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：169 ms Tokens：- 时间：2026-08-30 16:06:44

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：5519 ms Tokens：180 时间：2026-08-30 16:06:44

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：5710 ms Tokens：163 时间：2026-08-30 16:06:44

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：4299 ms Tokens：171 时间：2026-08-30 16:06:49

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	1038	200	113
DeepSeek-v4-pro-01	成功	1063	200	113
DeepSeek-v4-pro-01	成功	1518	200	113
DeepSeek-v4-pro-03	成功	2403	200	113
DeepSeek-v4-pro-03	成功	1420	200	113
DeepSeek-v4-pro-03	成功	1151	200	113
DeepSeek-v4-pro-04	成功	1486	200	113
DeepSeek-v4-pro-04	成功	1029	200	113
DeepSeek-v4-pro-04	成功	1402	200	113
DeepSeek-v4-pro-02	成功	1611	200	113
DeepSeek-v4-pro-02	成功	1007	200	113
DeepSeek-v4-pro-02	成功	1527	200	113
jd-gemini-3.1-pro-preview	成功	2551	200	26
jd-gemini-3.1-pro-preview	成功	3124	200	27
jd-gemini-3.1-pro-preview	成功	4861	200	26
腾讯 Gemini 3.5 Flash	成功	4367	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	4210	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	4301	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	3256	200	189	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3763	200	213	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	524	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	8876	200	489	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	666	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	543	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	541	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	466	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2473	200	115
Kimi K3 - Aliyun Bailian	成功	2096	200	115
Kimi K3 - Aliyun Bailian	成功	3554	200	115
Kimi K3	成功	4905	200	189	{"status":"ok","message":"stable"}
Kimi K3	成功	5661	200	192	{"status":"ok","message":"stable"}
Kimi K3	成功	4702	200	186	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2340	200	115
Kimi K3 - TopenRouter	成功	3019	200	115
Qwen3.8-Max	成功	1611	200	125	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2511	200	115
Qwen3.8-Max	成功	1743	200	127	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	214	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	158	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	1606	200	125	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	169	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	5519	200	180	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5710	200	163	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4299	200	171	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细