Model Channel Lab

测试结果

Run ID: 20260827-235310-001ab841

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟6342 ms

P95 / Tokens38890 / 4397

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	1199	1519	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1240	1371	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1362	1580	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1416	1471	339
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2298	2456	345
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2551	2797	409
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	3615	4218	81
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	可用	4394	7365	427
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5186	6088	883
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5287	6397	473
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	可用	5608	5725	78
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	41953	44062	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：1272 ms Tokens：113 时间：2026-08-27 23:51:13

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1580 ms Tokens：113 时间：2026-08-27 23:51:13

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1234 ms Tokens：113 时间：2026-08-27 23:51:15

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1519 ms Tokens：113 时间：2026-08-27 23:51:15

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：837 ms Tokens：113 时间：2026-08-27 23:51:16

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1242 ms Tokens：113 时间：2026-08-27 23:51:17

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1105 ms Tokens：113 时间：2026-08-27 23:51:17

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1246 ms Tokens：113 时间：2026-08-27 23:51:18

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1371 ms Tokens：113 时间：2026-08-27 23:51:18

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1463 ms Tokens：113 时间：2026-08-27 23:51:19

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1471 ms Tokens：113 时间：2026-08-27 23:51:19

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1316 ms Tokens：113 时间：2026-08-27 23:51:20

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：2944 ms Tokens：27 时间：2026-08-27 23:51:22

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：4218 ms Tokens：27 时间：2026-08-27 23:51:21

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：3683 ms Tokens：27 时间：2026-08-27 23:51:25

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：5582 ms Tokens：26 时间：2026-08-27 23:51:25

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

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：5519 ms Tokens：26 时间：2026-08-27 23:51:28

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：5725 ms Tokens：26 时间：2026-08-27 23:51:31

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：6088 ms Tokens：346 时间：2026-08-27 23:51:34

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5858 ms Tokens：331 时间：2026-08-27 23:51:36

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：532 ms Tokens：- 时间：2026-08-27 23:51:42

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：479 ms Tokens：- 时间：2026-08-27 23:51:43

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：507 ms Tokens：- 时间：2026-08-27 23:51:43

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：3614 ms Tokens：206 时间：2026-08-27 23:51:40

JSON

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

#25 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：480 ms Tokens：- 时间：2026-08-27 23:51:44

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：521 ms Tokens：- 时间：2026-08-27 23:51:44

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：494 ms Tokens：- 时间：2026-08-27 23:51:44

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：2005 ms Tokens：115 时间：2026-08-27 23:51:44

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2456 ms Tokens：115 时间：2026-08-27 23:51:45

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2433 ms Tokens：115 时间：2026-08-27 23:51:46

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：44062 ms Tokens：115 时间：2026-08-27 23:51:47

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：42909 ms Tokens：115 时间：2026-08-27 23:51:49

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3418 ms Tokens：65 时间：2026-08-27 23:52:32

JSON

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

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：7365 ms Tokens：181 时间：2026-08-27 23:52:35

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2399 ms Tokens：181 时间：2026-08-27 23:52:42

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2797 ms Tokens：146 时间：2026-08-27 23:52:45

JSON

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

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2575 ms Tokens：127 时间：2026-08-27 23:52:48

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2282 ms Tokens：136 时间：2026-08-27 23:52:50

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：184 ms Tokens：- 时间：2026-08-27 23:52:52

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：124 ms Tokens：- 时间：2026-08-27 23:52:53

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：168 ms Tokens：- 时间：2026-08-27 23:52:53

JSON

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

#42 yulin-gemini-3.7-flash-high 成功 HTTP 200

模型：gemini-3.7-flash-high 延迟：6397 ms Tokens：165 时间：2026-08-27 23:52:53

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：4910 ms Tokens：165 时间：2026-08-27 23:52:59

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：4555 ms Tokens：143 时间：2026-08-27 23:53:04

JSON

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

#45 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：38890 ms Tokens：115 时间：2026-08-27 23:52:31

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"}

表格明细

渠道	状态	延迟 ms	HTTP	Tokens	输出 / 错误
DeepSeek-v4-pro-01	成功	1272	200	113
DeepSeek-v4-pro-01	成功	1580	200	113
DeepSeek-v4-pro-01	成功	1234	200	113
DeepSeek-v4-pro-03	成功	1519	200	113
DeepSeek-v4-pro-03	成功	837	200	113
DeepSeek-v4-pro-03	成功	1242	200	113
DeepSeek-v4-pro-04	成功	1105	200	113
DeepSeek-v4-pro-04	成功	1246	200	113
DeepSeek-v4-pro-04	成功	1371	200	113
DeepSeek-v4-pro-02	成功	1463	200	113
DeepSeek-v4-pro-02	成功	1471	200	113
DeepSeek-v4-pro-02	成功	1316	200	113
jd-gemini-3.1-pro-preview	成功	2944	200	27
jd-gemini-3.1-pro-preview	成功	4218	200	27
jd-gemini-3.1-pro-preview	成功	3683	200	27
腾讯 Gemini 3.5 Flash	成功	5582	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	5519	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	5725	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
qwen3.6-plus	成功	6088	200	346	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	5858	200	331	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	532	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	479	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	507	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	3614	200	206	```json {"status":"ok","message":"stable"} ```
yuling-gpt-5.5	失败	480	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	521	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	494	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2005	200	115
Kimi K3 - Aliyun Bailian	成功	2456	200	115
Kimi K3 - Aliyun Bailian	成功	2433	200	115
Kimi K3	成功	44062	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	42909	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	3418	200	65	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	7365	200	181
Kimi K3 - TopenRouter	成功	2399	200	181
Qwen3.8-Max	成功	2797	200	146	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2575	200	127	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2282	200	136	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	184	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	124	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	168	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	6397	200	165	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4910	200	165	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4555	200	143	{"status":"ok","message":"stable"}
Kimi K3	成功	38890	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"}

历史详情

测试结果

结果明细

表格明细