Model Channel Lab

测试结果

Run ID: 20260827-062955-3fd9dfa7

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3101 ms

P95 / Tokens5425 / 4150

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	908	989	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	988	1108	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1003	1071	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1164	1343	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2268	2640	396
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2681	2755	345
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	可用	3768	5425	348
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	4011	4213	345
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	4082	4369	695
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4339	4432	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5163	5942	508
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	可用	6833	15292	79
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：1086 ms Tokens：113 时间：2026-08-27 06:28:54

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1108 ms Tokens：113 时间：2026-08-27 06:28:54

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：770 ms Tokens：113 时间：2026-08-27 06:28:56

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：791 ms Tokens：113 时间：2026-08-27 06:28:56

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：944 ms Tokens：113 时间：2026-08-27 06:28:56

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：989 ms Tokens：113 时间：2026-08-27 06:28:56

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1066 ms Tokens：113 时间：2026-08-27 06:28:57

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1084 ms Tokens：113 时间：2026-08-27 06:28:57

JSON

无输出内容。

#9 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1064 ms Tokens：113 时间：2026-08-27 06:28:58

JSON

无输出内容。

#10 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1343 ms Tokens：113 时间：2026-08-27 06:28:58

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：876 ms Tokens：113 时间：2026-08-27 06:29:00

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1071 ms Tokens：113 时间：2026-08-27 06:29:00

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：2630 ms Tokens：26 时间：2026-08-27 06:29:00

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：2579 ms Tokens：26 时间：2026-08-27 06:29:01

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：4274 ms Tokens：26 时间：2026-08-27 06:29:03

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：4432 ms Tokens：26 时间：2026-08-27 06:29:08

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4313 ms Tokens：26 时间：2026-08-27 06:29:12

JSON

#18 jd-gemini-3.1-pro-preview 成功 HTTP 200

模型：gemini-3.1-pro-preview 延迟：15292 ms Tokens：27 时间：2026-08-27 06:29:03

JSON

无输出内容。

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3661 ms Tokens：209 时间：2026-08-27 06:29:16

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4216 ms Tokens：243 时间：2026-08-27 06:29:18

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：522 ms Tokens：- 时间：2026-08-27 06:29:23

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：554 ms Tokens：- 时间：2026-08-27 06:29:23

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：522 ms Tokens：- 时间：2026-08-27 06:29:24

JSON

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

#24 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4369 ms Tokens：243 时间：2026-08-27 06:29:20

JSON

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

#25 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：530 ms Tokens：- 时间：2026-08-27 06:29:24

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：510 ms Tokens：- 时间：2026-08-27 06:29:24

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：515 ms Tokens：- 时间：2026-08-27 06:29:25

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：2755 ms Tokens：115 时间：2026-08-27 06:29:25

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2724 ms Tokens：115 时间：2026-08-27 06:29:25

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2566 ms Tokens：115 时间：2026-08-27 06:29:28

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4213 ms Tokens：115 时间：2026-08-27 06:29:28

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"}

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4031 ms Tokens：115 时间：2026-08-27 06:29:30

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 成功 HTTP 200

模型：kimi-k3 延迟：3789 ms Tokens：115 时间：2026-08-27 06:29:32

JSON

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

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3057 ms Tokens：116 时间：2026-08-27 06:29:34

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2824 ms Tokens：116 时间：2026-08-27 06:29:36

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2004 ms Tokens：135 时间：2026-08-27 06:29:39

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：5425 ms Tokens：116 时间：2026-08-27 06:29:37

JSON

无输出内容。

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2640 ms Tokens：134 时间：2026-08-27 06:29:41

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：235 ms Tokens：- 时间：2026-08-27 06:29:43

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：173 ms Tokens：- 时间：2026-08-27 06:29:44

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：199 ms Tokens：- 时间：2026-08-27 06:29:44

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：2160 ms Tokens：127 时间：2026-08-27 06:29:43

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：5223 ms Tokens：152 时间：2026-08-27 06:29:44

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：4326 ms Tokens：175 时间：2026-08-27 06:29:45

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：5942 ms Tokens：181 时间：2026-08-27 06:29:49

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	1086	200	113
DeepSeek-v4-pro-01	成功	1108	200	113
DeepSeek-v4-pro-01	成功	770	200	113
DeepSeek-v4-pro-03	成功	791	200	113
DeepSeek-v4-pro-03	成功	944	200	113
DeepSeek-v4-pro-03	成功	989	200	113
DeepSeek-v4-pro-04	成功	1066	200	113
DeepSeek-v4-pro-04	成功	1084	200	113
DeepSeek-v4-pro-02	成功	1064	200	113
DeepSeek-v4-pro-04	成功	1343	200	113
DeepSeek-v4-pro-02	成功	876	200	113
DeepSeek-v4-pro-02	成功	1071	200	113
jd-gemini-3.1-pro-preview	成功	2630	200	26
jd-gemini-3.1-pro-preview	成功	2579	200	26
腾讯 Gemini 3.5 Flash	成功	4274	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	4432	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	4313	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
jd-gemini-3.1-pro-preview	成功	15292	200	27
qwen3.6-plus	成功	3661	200	209	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4216	200	243	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	522	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	554	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	522	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	4369	200	243	{"status":"ok","message":"stable"}
yuling-gpt-5.5	失败	530	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	510	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	515	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2755	200	115
Kimi K3 - Aliyun Bailian	成功	2724	200	115
Kimi K3 - Aliyun Bailian	成功	2566	200	115
Kimi K3	成功	4213	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	成功	4031	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	成功	3789	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a JSON object: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	3057	200	116
Kimi K3 - TopenRouter	成功	2824	200	116
Qwen3.8-Max	成功	2004	200	135	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	5425	200	116
Qwen3.8-Max	成功	2640	200	134	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	235	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	173	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	199	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2160	200	127	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5223	200	152	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4326	200	175	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5942	200	181	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细