Model Channel Lab

测试结果

Run ID: 20260828-025638-5cbd45fa

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟4396 ms

P95 / Tokens7360 / 4449

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	940	1011	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1172	1319	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1207	1335	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1438	1938	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	1968	2243	389
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2563	2984	79
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	4257	4651	510
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4449	4543	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	4644	7360	495
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5009	5886	852
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	可用	7305	13622	345
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	17801	45675	345
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：1326 ms Tokens：113 时间：2026-08-28 02:55:14

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1938 ms Tokens：113 时间：2026-08-28 02:55:14

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1051 ms Tokens：113 时间：2026-08-28 02:55:15

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1335 ms Tokens：113 时间：2026-08-28 02:55:16

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1249 ms Tokens：113 时间：2026-08-28 02:55:16

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1039 ms Tokens：113 时间：2026-08-28 02:55:17

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1011 ms Tokens：113 时间：2026-08-28 02:55:17

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：910 ms Tokens：113 时间：2026-08-28 02:55:18

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：899 ms Tokens：113 时间：2026-08-28 02:55:18

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1172 ms Tokens：113 时间：2026-08-28 02:55:19

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1319 ms Tokens：113 时间：2026-08-28 02:55:19

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1026 ms Tokens：113 时间：2026-08-28 02:55:20

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：2519 ms Tokens：26 时间：2026-08-28 02:55:20

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：2188 ms Tokens：26 时间：2026-08-28 02:55:21

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：2984 ms Tokens：27 时间：2026-08-28 02:55:23

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：4438 ms Tokens：26 时间：2026-08-28 02:55:23

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：4543 ms Tokens：26 时间：2026-08-28 02:55:26

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4366 ms Tokens：26 时间：2026-08-28 02:55:28

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3364 ms Tokens：190 时间：2026-08-28 02:55:32

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5777 ms Tokens：331 时间：2026-08-28 02:55:30

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：503 ms Tokens：- 时间：2026-08-28 02:55:36

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：494 ms Tokens：- 时间：2026-08-28 02:55:37

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：521 ms Tokens：- 时间：2026-08-28 02:55:37

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：437 ms Tokens：- 时间：2026-08-28 02:55:38

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：480 ms Tokens：- 时间：2026-08-28 02:55:38

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：443 ms Tokens：- 时间：2026-08-28 02:55:39

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：5886 ms Tokens：331 时间：2026-08-28 02:55:35

JSON

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

#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：6562 ms Tokens：115 时间：2026-08-28 02:55:41

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1732 ms Tokens：115 时间：2026-08-28 02:55:48

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：13622 ms Tokens：115 时间：2026-08-28 02:55:39

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：3939 ms Tokens：115 时间：2026-08-28 02:55:50

JSON

{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：3790 ms Tokens：115 时间：2026-08-28 02:55:53

JSON

{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4651 ms Tokens：160 时间：2026-08-28 02:55:57

JSON

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

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4464 ms Tokens：176 时间：2026-08-28 02:56:02

JSON

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

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3658 ms Tokens：174 时间：2026-08-28 02:56:06

JSON

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

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2243 ms Tokens：137 时间：2026-08-28 02:56:10

JSON

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

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1854 ms Tokens：127 时间：2026-08-28 02:56:12

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1808 ms Tokens：125 时间：2026-08-28 02:56:14

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：201 ms Tokens：- 时间：2026-08-28 02:56:16

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：162 ms Tokens：- 时间：2026-08-28 02:56:16

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：194 ms Tokens：- 时间：2026-08-28 02:56:16

JSON

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

#42 yulin-gemini-3.7-flash-high 成功 HTTP 200

模型：gemini-3.7-flash-high 延迟：3748 ms Tokens：176 时间：2026-08-28 02:56:17

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：2824 ms Tokens：164 时间：2026-08-28 02:56:20

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：7360 ms Tokens：155 时间：2026-08-28 02:56:23

JSON

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

#45 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：45675 ms Tokens：115 时间：2026-08-28 02:55:53

JSON

{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user wants me to reply with only JSON: {\"status\":\"ok\",\"message"}, "logprobs": null, "finish_reason": "length"}

表格明细

渠道	状态	延迟 ms	HTTP	Tokens	输出 / 错误
DeepSeek-v4-pro-01	成功	1326	200	113
DeepSeek-v4-pro-01	成功	1938	200	113
DeepSeek-v4-pro-01	成功	1051	200	113
DeepSeek-v4-pro-03	成功	1335	200	113
DeepSeek-v4-pro-03	成功	1249	200	113
DeepSeek-v4-pro-03	成功	1039	200	113
DeepSeek-v4-pro-04	成功	1011	200	113
DeepSeek-v4-pro-04	成功	910	200	113
DeepSeek-v4-pro-04	成功	899	200	113
DeepSeek-v4-pro-02	成功	1172	200	113
DeepSeek-v4-pro-02	成功	1319	200	113
DeepSeek-v4-pro-02	成功	1026	200	113
jd-gemini-3.1-pro-preview	成功	2519	200	26
jd-gemini-3.1-pro-preview	成功	2188	200	26
jd-gemini-3.1-pro-preview	成功	2984	200	27
腾讯 Gemini 3.5 Flash	成功	4438	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	4543	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	4366	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	3364	200	190	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	5777	200	331	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	503	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	494	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	521	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	437	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	480	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	443	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	5886	200	331	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	6562	200	115
Kimi K3 - Aliyun Bailian	成功	1732	200	115
Kimi K3 - Aliyun Bailian	成功	13622	200	115
Kimi K3	成功	3939	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	3790	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	4651	200	160	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	4464	200	176	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	3658	200	174	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2243	200	137	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1854	200	127	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1808	200	125	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	201	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	162	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	194	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	3748	200	176	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	2824	200	164	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	7360	200	155	{"status":"ok","message":"stable"}
Kimi K3	成功	45675	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user wants me to reply with only JSON: {\"status\":\"ok\",\"message"}, "logprobs": null, "finish_reason": "length"}

历史详情

测试结果

结果明细

表格明细