Model Channel Lab

测试结果

Run ID: 20260828-035751-b1c028e8

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3793 ms

P95 / Tokens7485 / 4336

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-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1114	1156	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1139	1250	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1148	1307	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1221	1317	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	1994	2302	389
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	可用	3686	5738	345
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	4191	4633	720
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	可用	4481	5084	497
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	4884	5384	528
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	可用	5533	5683	78
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	可用	7521	17976	78
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	8607	11238	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：1130 ms Tokens：113 时间：2026-08-28 03:56:39

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1156 ms Tokens：113 时间：2026-08-28 03:56:39

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1057 ms Tokens：113 时间：2026-08-28 03:56:40

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1118 ms Tokens：113 时间：2026-08-28 03:56:40

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1228 ms Tokens：113 时间：2026-08-28 03:56:41

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1317 ms Tokens：113 时间：2026-08-28 03:56:41

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：964 ms Tokens：113 时间：2026-08-28 03:56:42

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1175 ms Tokens：113 时间：2026-08-28 03:56:42

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1307 ms Tokens：113 时间：2026-08-28 03:56:43

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1142 ms Tokens：113 时间：2026-08-28 03:56:43

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1026 ms Tokens：113 时间：2026-08-28 03:56:44

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1250 ms Tokens：113 时间：2026-08-28 03:56:45

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：2149 ms Tokens：26 时间：2026-08-28 03:56:46

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：2440 ms Tokens：26 时间：2026-08-28 03:56:45

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：5683 ms Tokens：26 时间：2026-08-28 03:56:48

JSON

{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I

#16 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：5591 ms Tokens：26 时间：2026-08-28 03:56:54

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：5326 ms Tokens：26 时间：2026-08-28 03:56:59

JSON

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

模型：gemini-3.1-pro-preview 延迟：17976 ms Tokens：26 时间：2026-08-28 03:56:48

JSON

无输出内容。

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4203 ms Tokens：243 时间：2026-08-28 03:57:05

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3739 ms Tokens：209 时间：2026-08-28 03:57:06

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：546 ms Tokens：- 时间：2026-08-28 03:57:10

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：463 ms Tokens：- 时间：2026-08-28 03:57:10

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：530 ms Tokens：- 时间：2026-08-28 03:57:11

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：508 ms Tokens：- 时间：2026-08-28 03:57:11

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：506 ms Tokens：- 时间：2026-08-28 03:57:12

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：520 ms Tokens：- 时间：2026-08-28 03:57:12

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：4633 ms Tokens：268 时间：2026-08-28 03:57:09

JSON

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

#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2921 ms Tokens：115 时间：2026-08-28 03:57:13

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2400 ms Tokens：115 时间：2026-08-28 03:57:16

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：5738 ms Tokens：115 时间：2026-08-28 03:57:13

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：7485 ms Tokens：115 时间：2026-08-28 03:57:18

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：11238 ms Tokens：115 时间：2026-08-28 03:57:19

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：7100 ms Tokens：115 时间：2026-08-28 03:57:26

JSON

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

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3749 ms Tokens：162 时间：2026-08-28 03:57:30

JSON

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

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4610 ms Tokens：172 时间：2026-08-28 03:57:33

JSON

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

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1778 ms Tokens：127 时间：2026-08-28 03:57:37

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：5084 ms Tokens：163 时间：2026-08-28 03:57:34

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1902 ms Tokens：126 时间：2026-08-28 03:57:39

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：196 ms Tokens：- 时间：2026-08-28 03:57:41

JSON

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

#40 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2302 ms Tokens：136 时间：2026-08-28 03:57:39

JSON

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

#41 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：189 ms Tokens：- 时间：2026-08-28 03:57:41

JSON

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

#42 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：191 ms Tokens：- 时间：2026-08-28 03:57:41

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：4721 ms Tokens：161 时间：2026-08-28 03:57:41

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：5384 ms Tokens：175 时间：2026-08-28 03:57:41

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：4549 ms Tokens：192 时间：2026-08-28 03:57:46

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	1130	200	113
DeepSeek-v4-pro-01	成功	1156	200	113
DeepSeek-v4-pro-01	成功	1057	200	113
DeepSeek-v4-pro-03	成功	1118	200	113
DeepSeek-v4-pro-03	成功	1228	200	113
DeepSeek-v4-pro-03	成功	1317	200	113
DeepSeek-v4-pro-04	成功	964	200	113
DeepSeek-v4-pro-04	成功	1175	200	113
DeepSeek-v4-pro-04	成功	1307	200	113
DeepSeek-v4-pro-02	成功	1142	200	113
DeepSeek-v4-pro-02	成功	1026	200	113
DeepSeek-v4-pro-02	成功	1250	200	113
jd-gemini-3.1-pro-preview	成功	2149	200	26
jd-gemini-3.1-pro-preview	成功	2440	200	26
腾讯 Gemini 3.5 Flash	成功	5683	200	26	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "My Internal Monologue on Summarizing and the User's Expertise\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. First-Person Perspective: I need to inhabit the thoughts described in the text, speaking as if they are my own internal musings. This isn't about me reporting on the thoughts; it's about me having them.\n2. Fulsome Summary of Thought Process: This means I can't just give a brief overview. I need to go deep into the how and why of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. Target Audience is Expert: The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. Specific Starting Header: The summary must begin with a bolded header, and the example given is \"My Summary:\". I
腾讯 Gemini 3.5 Flash	成功	5591	200	26	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "My Internal Monologue on Summarizing and the User's Expertise\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. First-Person Perspective: I need to inhabit the thoughts described in the text, speaking as if they are my own internal musings. This isn't about me reporting on the thoughts; it's about me having them.\n2. Fulsome Summary of Thought Process: This means I can't just give a brief overview. I need to go deep into the how and why of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. Target Audience is Expert: The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. Specific Starting Header: The summary must begin with a bolded header, and the example given is \"My Summary:\". I
腾讯 Gemini 3.5 Flash	成功	5326	200	26	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "My Internal Monologue on Summarizing and the User's Expertise\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. First-Person Perspective: I need to inhabit the thoughts described in the text, speaking as if they are my own internal musings. This isn't about me reporting on the thoughts; it's about me having them.\n2. Fulsome Summary of Thought Process: This means I can't just give a brief overview. I need to go deep into the how and why of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. Target Audience is Expert: The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. Specific Starting Header: The summary must begin with a bolded header, and the example given is \"My Summary:\". I
jd-gemini-3.1-pro-preview	成功	17976	200	26
qwen3.6-plus	成功	4203	200	243	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3739	200	209	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	546	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	463	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	530	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	506	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	520	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	4633	200	268	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	2921	200	115
Kimi K3 - Aliyun Bailian	成功	2400	200	115
Kimi K3 - Aliyun Bailian	成功	5738	200	115
Kimi K3	成功	7485	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only a JSON: {\"status\":\"ok"}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	11238	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	7100	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to only reply with a specific JSON: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	3749	200	162	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	4610	200	172	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1778	200	127	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	5084	200	163	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1902	200	126	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	196	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2302	200	136	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	189	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	191	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	4721	200	161	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5384	200	175	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4549	200	192	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细