Model Channel Lab

测试结果

Run ID: 20260827-093248-984bb334

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟2666 ms

P95 / Tokens4693 / 4098

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-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1183	1207	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1223	1679	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1338	1504	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1351	1696	339
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1836	2308	345
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2039	2417	430
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2771	2949	79
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	稳定	3130	3624	430
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	3413	4210	348
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	4120	4692	687
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4436	4693	78
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	5156	6561	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：1145 ms Tokens：113 时间：2026-08-27 09:31:57

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1365 ms Tokens：113 时间：2026-08-27 09:31:57

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1504 ms Tokens：113 时间：2026-08-27 09:31:58

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1329 ms Tokens：113 时间：2026-08-27 09:31:59

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1029 ms Tokens：113 时间：2026-08-27 09:32:00

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1696 ms Tokens：113 时间：2026-08-27 09:32:00

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1296 ms Tokens：113 时间：2026-08-27 09:32:01

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：696 ms Tokens：113 时间：2026-08-27 09:32:02

JSON

无输出内容。

#9 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1185 ms Tokens：113 时间：2026-08-27 09:32:02

JSON

无输出内容。

#10 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1679 ms Tokens：113 时间：2026-08-27 09:32:02

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1159 ms Tokens：113 时间：2026-08-27 09:32:04

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1207 ms Tokens：113 时间：2026-08-27 09:32:04

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：2583 ms Tokens：26 时间：2026-08-27 09:32:05

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：2949 ms Tokens：27 时间：2026-08-27 09:32:05

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：2781 ms Tokens：26 时间：2026-08-27 09:32:07

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：4693 ms Tokens：26 时间：2026-08-27 09:32:08

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：4409 ms Tokens：26 时间：2026-08-27 09:32:10

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4207 ms Tokens：26 时间：2026-08-27 09:32:13

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3665 ms Tokens：206 时间：2026-08-27 09:32:14

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4692 ms Tokens：268 时间：2026-08-27 09:32:17

JSON

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

#21 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4004 ms Tokens：213 时间：2026-08-27 09:32:18

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：530 ms Tokens：- 时间：2026-08-27 09:32:22

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：525 ms Tokens：- 时间：2026-08-27 09:32:22

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：517 ms Tokens：- 时间：2026-08-27 09:32:22

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：508 ms Tokens：- 时间：2026-08-27 09:32:23

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：475 ms Tokens：- 时间：2026-08-27 09:32:23

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：462 ms Tokens：- 时间：2026-08-27 09:32:23

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：1804 ms Tokens：115 时间：2026-08-27 09:32:24

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2308 ms Tokens：115 时间：2026-08-27 09:32:23

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1396 ms Tokens：115 时间：2026-08-27 09:32:25

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5678 ms Tokens：115 时间：2026-08-27 09:32:26

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"}

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6561 ms Tokens：115 时间：2026-08-27 09:32:27

JSON

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

#33 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：3230 ms Tokens：115 时间：2026-08-27 09:32:31

JSON

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

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3469 ms Tokens：116 时间：2026-08-27 09:32:33

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2562 ms Tokens：116 时间：2026-08-27 09:32:34

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2417 ms Tokens：158 时间：2026-08-27 09:32:37

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4210 ms Tokens：116 时间：2026-08-27 09:32:37

JSON

无输出内容。

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1901 ms Tokens：134 时间：2026-08-27 09:32:39

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：153 ms Tokens：- 时间：2026-08-27 09:32:41

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：157 ms Tokens：- 时间：2026-08-27 09:32:41

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：171 ms Tokens：- 时间：2026-08-27 09:32:42

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：1801 ms Tokens：138 时间：2026-08-27 09:32:41

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：2550 ms Tokens：146 时间：2026-08-27 09:32:42

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：3218 ms Tokens：144 时间：2026-08-27 09:32:43

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：3624 ms Tokens：140 时间：2026-08-27 09:32:44

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	1145	200	113
DeepSeek-v4-pro-01	成功	1365	200	113
DeepSeek-v4-pro-01	成功	1504	200	113
DeepSeek-v4-pro-03	成功	1329	200	113
DeepSeek-v4-pro-03	成功	1029	200	113
DeepSeek-v4-pro-03	成功	1696	200	113
DeepSeek-v4-pro-04	成功	1296	200	113
DeepSeek-v4-pro-04	成功	696	200	113
DeepSeek-v4-pro-02	成功	1185	200	113
DeepSeek-v4-pro-04	成功	1679	200	113
DeepSeek-v4-pro-02	成功	1159	200	113
DeepSeek-v4-pro-02	成功	1207	200	113
jd-gemini-3.1-pro-preview	成功	2583	200	26
jd-gemini-3.1-pro-preview	成功	2949	200	27
jd-gemini-3.1-pro-preview	成功	2781	200	26
腾讯 Gemini 3.5 Flash	成功	4693	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	4409	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	4207	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	3665	200	206	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4692	200	268	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4004	200	213	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	530	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	525	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	517	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	508	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	475	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	462	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	1804	200	115
Kimi K3 - Aliyun Bailian	成功	2308	200	115
Kimi K3 - Aliyun Bailian	成功	1396	200	115
Kimi K3	成功	5678	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"}
Kimi K3	成功	6561	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	3230	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	3469	200	116
Kimi K3 - TopenRouter	成功	2562	200	116
Qwen3.8-Max	成功	2417	200	158	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	4210	200	116
Qwen3.8-Max	成功	1901	200	134	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	153	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	157	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	171	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	1801	200	138	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	2550	200	146	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	3218	200	144	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	3624	200	140	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细