Model Channel Lab

测试结果

Run ID: 20260828-212248-bc98dff9

导出 JSON

总请求45

成功 / 失败33/12

成功率73.33%

平均延迟3107 ms

P95 / Tokens6798 / 4027

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	1107	1295	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1239	1572	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1306	1357	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1417	1466	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1684	2084	459
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2345	2860	383
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4307	4501	78
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	4400	5238	731
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	5793	7548	345
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	6607	8247	508
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	2/3	1/3	66.67%	33.33%	不稳定	2568	2752	52	timeout: The read operation timed out
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	1/3	2/3	33.33%	66.67%	不稳定	6798	6798	115	HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"52515bb7-bf8f-96e1-a321-5de48b03f21d"}
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：957 ms Tokens：113 时间：2026-08-28 21:21:29

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1190 ms Tokens：113 时间：2026-08-28 21:21:29

JSON

无输出内容。

#3 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1316 ms Tokens：113 时间：2026-08-28 21:21:31

JSON

无输出内容。

#4 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1572 ms Tokens：113 时间：2026-08-28 21:21:30

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1246 ms Tokens：113 时间：2026-08-28 21:21:32

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1357 ms Tokens：113 时间：2026-08-28 21:21:32

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1460 ms Tokens：113 时间：2026-08-28 21:21:33

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1327 ms Tokens：113 时间：2026-08-28 21:21:33

JSON

无输出内容。

#9 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1295 ms Tokens：113 时间：2026-08-28 21:21:35

JSON

无输出内容。

#10 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1466 ms Tokens：113 时间：2026-08-28 21:21:35

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1087 ms Tokens：113 时间：2026-08-28 21:21:36

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：939 ms Tokens：113 时间：2026-08-28 21:21:36

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：2752 ms Tokens：26 时间：2026-08-28 21:21:37

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：2384 ms Tokens：26 时间：2026-08-28 21:21:40

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：4501 ms Tokens：26 时间：2026-08-28 21:21:42

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：4222 ms Tokens：26 时间：2026-08-28 21:21:47

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4200 ms Tokens：26 时间：2026-08-28 21:21:51

JSON

#18 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4545 ms Tokens：241 时间：2026-08-28 21:21:55

JSON

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

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3418 ms Tokens：193 时间：2026-08-28 21:22:00

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：30195 ms Tokens：- 时间：2026-08-28 21:21:37

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：510 ms Tokens：- 时间：2026-08-28 21:22:07

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：511 ms Tokens：- 时间：2026-08-28 21:22:08

JSON

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

#23 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5238 ms Tokens：297 时间：2026-08-28 21:22:03

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：512 ms Tokens：- 时间：2026-08-28 21:22:08

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：532 ms Tokens：- 时间：2026-08-28 21:22:08

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：447 ms Tokens：- 时间：2026-08-28 21:22:09

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：465 ms Tokens：- 时间：2026-08-28 21:22:09

JSON

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

#28 Kimi K3 - Aliyun Bailian 失败 HTTP 429

模型：kimi/kimi-k3 延迟：8926 ms Tokens：- 时间：2026-08-28 21:22:09

JSON

HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"52515bb7-bf8f-96e1-a321-5de48b03f21d"}

#29 Kimi K3 - Aliyun Bailian 失败 HTTP 429

模型：kimi/kimi-k3 延迟：9297 ms Tokens：- 时间：2026-08-28 21:22:09

JSON

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：6798 ms Tokens：115 时间：2026-08-28 21:22:18

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：7548 ms Tokens：115 时间：2026-08-28 21:22:19

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：4757 ms Tokens：115 时间：2026-08-28 21:22:25

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"}

#33 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5075 ms Tokens：115 时间：2026-08-28 21:22:26

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：2084 ms Tokens：153 时间：2026-08-28 21:22:30

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1305 ms Tokens：153 时间：2026-08-28 21:22:31

JSON

无输出内容。

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1665 ms Tokens：153 时间：2026-08-28 21:22:32

JSON

无输出内容。

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1700 ms Tokens：127 时间：2026-08-28 21:22:33

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2860 ms Tokens：117 时间：2026-08-28 21:22:33

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：164 ms Tokens：- 时间：2026-08-28 21:22:36

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：135 ms Tokens：- 时间：2026-08-28 21:22:36

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：2477 ms Tokens：139 时间：2026-08-28 21:22:34

JSON

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

#42 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：172 ms Tokens：- 时间：2026-08-28 21:22:37

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：5430 ms Tokens：186 时间：2026-08-28 21:22:37

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：8247 ms Tokens：151 时间：2026-08-28 21:22:37

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：6144 ms Tokens：171 时间：2026-08-28 21:22:42

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	957	200	113
DeepSeek-v4-pro-01	成功	1190	200	113
DeepSeek-v4-pro-03	成功	1316	200	113
DeepSeek-v4-pro-01	成功	1572	200	113
DeepSeek-v4-pro-03	成功	1246	200	113
DeepSeek-v4-pro-03	成功	1357	200	113
DeepSeek-v4-pro-04	成功	1460	200	113
DeepSeek-v4-pro-04	成功	1327	200	113
DeepSeek-v4-pro-02	成功	1295	200	113
DeepSeek-v4-pro-04	成功	1466	200	113
DeepSeek-v4-pro-02	成功	1087	200	113
DeepSeek-v4-pro-02	成功	939	200	113
jd-gemini-3.1-pro-preview	成功	2752	200	26
jd-gemini-3.1-pro-preview	成功	2384	200	26
腾讯 Gemini 3.5 Flash	成功	4501	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	4222	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	4200	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	4545	200	241	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3418	200	193	{"status":"ok","message":"stable"}
jd-gemini-3.1-pro-preview	失败	30195	-	-	timeout: The read operation timed out
pixflow-gemini-3.1-pro-preview	失败	510	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	511	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	5238	200	297	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	512	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	532	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	447	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	465	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	失败	8926	429	-	HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"52515bb7-bf8f-96e1-a321-5de48b03f21d"}
Kimi K3 - Aliyun Bailian	失败	9297	429	-	HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"edefc647-020f-9633-aa0e-a3538a5035b0"}
Kimi K3 - Aliyun Bailian	成功	6798	200	115
Kimi K3	成功	7548	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	4757	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	5075	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	2084	200	153
Kimi K3 - TopenRouter	成功	1305	200	153
Kimi K3 - TopenRouter	成功	1665	200	153
Qwen3.8-Max	成功	1700	200	127	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2860	200	117	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	164	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	135	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2477	200	139	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	172	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	5430	200	186	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	8247	200	151	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6144	200	171	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细