Model Channel Lab

测试结果

Run ID: 20260828-202129-07a4e3e4

导出 JSON

总请求45

成功 / 失败34/11

成功率75.56%

平均延迟3020 ms

P95 / Tokens8596 / 4267

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	1064	1375	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1147	1309	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1180	1378	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1218	1455	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1774	2312	459
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	1824	1991	390
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	稳定	2727	2786	490
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4392	4542	78
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5017	5950	867
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	6055	10042	345
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	2/3	1/3	66.67%	33.33%	不稳定	2931	3163	52	timeout: The read operation timed out
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	2/3	1/3	66.67%	33.33%	不稳定	8820	9044	230	HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"78ab3207-898b-9169-b838-21829856092a"}
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：1281 ms Tokens：113 时间：2026-08-28 20:20:17

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1378 ms Tokens：113 时间：2026-08-28 20:20:17

JSON

无输出内容。

#3 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：729 ms Tokens：113 时间：2026-08-28 20:20:19

JSON

无输出内容。

#4 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：881 ms Tokens：113 时间：2026-08-28 20:20:19

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1089 ms Tokens：113 时间：2026-08-28 20:20:20

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1375 ms Tokens：113 时间：2026-08-28 20:20:19

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1053 ms Tokens：113 时间：2026-08-28 20:20:21

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1079 ms Tokens：113 时间：2026-08-28 20:20:21

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1309 ms Tokens：113 时间：2026-08-28 20:20:22

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1455 ms Tokens：113 时间：2026-08-28 20:20:22

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：899 ms Tokens：113 时间：2026-08-28 20:20:23

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1300 ms Tokens：113 时间：2026-08-28 20:20:23

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：2700 ms Tokens：26 时间：2026-08-28 20:20:24

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：3163 ms Tokens：26 时间：2026-08-28 20:20:27

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：4210 ms Tokens：26 时间：2026-08-28 20:20:30

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：4542 ms Tokens：26 时间：2026-08-28 20:20:34

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4425 ms Tokens：26 时间：2026-08-28 20:20:39

JSON

#18 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3317 ms Tokens：190 时间：2026-08-28 20:20:43

JSON

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

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5786 ms Tokens：331 时间：2026-08-28 20:20:46

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：30229 ms Tokens：- 时间：2026-08-28 20:20:25

JSON

timeout: The read operation timed out

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

模型：gemini-3.1-pro-preview 延迟：552 ms Tokens：- 时间：2026-08-28 20:20:55

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：524 ms Tokens：- 时间：2026-08-28 20:20:55

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：458 ms Tokens：- 时间：2026-08-28 20:20:56

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：552 ms Tokens：- 时间：2026-08-28 20:20:56

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：479 ms Tokens：- 时间：2026-08-28 20:20:57

JSON

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

#26 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5950 ms Tokens：346 时间：2026-08-28 20:20:52

JSON

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

#27 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：552 ms Tokens：- 时间：2026-08-28 20:20:57

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：8596 ms Tokens：115 时间：2026-08-28 20:20:58

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：9044 ms Tokens：115 时间：2026-08-28 20:20:58

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 失败 HTTP 429

模型：kimi/kimi-k3 延迟：5222 ms Tokens：- 时间：2026-08-28 20:21:07

JSON

HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"78ab3207-898b-9169-b838-21829856092a"}

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4017 ms Tokens：115 时间：2026-08-28 20:21:12

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：10042 ms Tokens：115 时间：2026-08-28 20:21:07

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2312 ms Tokens：153 时间：2026-08-28 20:21:17

JSON

无输出内容。

#34 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4106 ms Tokens：115 时间：2026-08-28 20:21:16

JSON

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

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1062 ms Tokens：153 时间：2026-08-28 20:21:20

JSON

无输出内容。

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1949 ms Tokens：153 时间：2026-08-28 20:21:19

JSON

无输出内容。

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1991 ms Tokens：138 时间：2026-08-28 20:21:21

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1642 ms Tokens：127 时间：2026-08-28 20:21:21

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：209 ms Tokens：- 时间：2026-08-28 20:21:23

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：171 ms Tokens：- 时间：2026-08-28 20:21:23

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：211 ms Tokens：- 时间：2026-08-28 20:21:23

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：1839 ms Tokens：125 时间：2026-08-28 20:21:23

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：2764 ms Tokens：144 时间：2026-08-28 20:21:24

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：2633 ms Tokens：185 时间：2026-08-28 20:21:25

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：2786 ms Tokens：161 时间：2026-08-28 20:21:26

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	1281	200	113
DeepSeek-v4-pro-01	成功	1378	200	113
DeepSeek-v4-pro-03	成功	729	200	113
DeepSeek-v4-pro-01	成功	881	200	113
DeepSeek-v4-pro-03	成功	1089	200	113
DeepSeek-v4-pro-03	成功	1375	200	113
DeepSeek-v4-pro-04	成功	1053	200	113
DeepSeek-v4-pro-04	成功	1079	200	113
DeepSeek-v4-pro-04	成功	1309	200	113
DeepSeek-v4-pro-02	成功	1455	200	113
DeepSeek-v4-pro-02	成功	899	200	113
DeepSeek-v4-pro-02	成功	1300	200	113
jd-gemini-3.1-pro-preview	成功	2700	200	26
jd-gemini-3.1-pro-preview	成功	3163	200	26
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	4542	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	4425	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	3317	200	190	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	5786	200	331	{"status":"ok","message":"stable"}
jd-gemini-3.1-pro-preview	失败	30229	-	-	timeout: The read operation timed out
pixflow-gemini-3.1-pro-preview	失败	552	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	524	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	458	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	552	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	479	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	5950	200	346	{"status":"ok","message":"stable"}
yuling-gpt-5.5	失败	552	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	8596	200	115
Kimi K3 - Aliyun Bailian	成功	9044	200	115
Kimi K3 - Aliyun Bailian	失败	5222	429	-	HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"78ab3207-898b-9169-b838-21829856092a"}
Kimi K3	成功	4017	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	10042	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	2312	200	153
Kimi K3	成功	4106	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to only reply with a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	1062	200	153
Kimi K3 - TopenRouter	成功	1949	200	153
Qwen3.8-Max	成功	1991	200	138	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1642	200	127	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	209	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
MiniMax H3 Context IR	失败	211	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	1839	200	125	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	2764	200	144	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	2633	200	185	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	2786	200	161	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细