Model Channel Lab

测试结果

Run ID: 20260828-045856-5c151ebf

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3411 ms

P95 / Tokens8309 / 4454

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-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	919	1114	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1125	1147	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1145	1622	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1157	1480	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2809	4045	394
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	3170	4739	304
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	3600	3646	624
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4560	4592	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	稳定	4639	4767	504
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	5089	5832	427
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	可用	5262	8865	345
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	可用	7451	9996	422
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：731 ms Tokens：113 时间：2026-08-28 04:57:51

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1480 ms Tokens：113 时间：2026-08-28 04:57:51

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1262 ms Tokens：113 时间：2026-08-28 04:57:52

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1117 ms Tokens：113 时间：2026-08-28 04:57:52

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：698 ms Tokens：113 时间：2026-08-28 04:57:54

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1622 ms Tokens：113 时间：2026-08-28 04:57:53

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：920 ms Tokens：113 时间：2026-08-28 04:57:54

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：724 ms Tokens：113 时间：2026-08-28 04:57:55

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1114 ms Tokens：113 时间：2026-08-28 04:57:55

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1117 ms Tokens：113 时间：2026-08-28 04:57:55

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1113 ms Tokens：113 时间：2026-08-28 04:57:56

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1147 ms Tokens：113 时间：2026-08-28 04:57:56

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：2240 ms Tokens：26 时间：2026-08-28 04:57:58

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：4739 ms Tokens：252 时间：2026-08-28 04:57:57

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：2532 ms Tokens：26 时间：2026-08-28 04:58:00

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：4592 ms Tokens：26 时间：2026-08-28 04:58:02

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

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4522 ms Tokens：26 时间：2026-08-28 04:58:02

JSON

#18 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3599 ms Tokens：209 时间：2026-08-28 04:58:07

JSON

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

#19 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4568 ms Tokens：26 时间：2026-08-28 04:58:07

JSON

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3556 ms Tokens：206 时间：2026-08-28 04:58:10

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：517 ms Tokens：- 时间：2026-08-28 04:58:14

JSON

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

#22 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3646 ms Tokens：209 时间：2026-08-28 04:58:11

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：547 ms Tokens：- 时间：2026-08-28 04:58:15

JSON

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

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

模型：gemini-3.1-pro-preview 延迟：488 ms Tokens：- 时间：2026-08-28 04:58:15

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：526 ms Tokens：- 时间：2026-08-28 04:58:15

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：499 ms Tokens：- 时间：2026-08-28 04:58:15

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：505 ms Tokens：- 时间：2026-08-28 04:58:16

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：4539 ms Tokens：115 时间：2026-08-28 04:58:16

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2384 ms Tokens：115 时间：2026-08-28 04:58:21

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：8865 ms Tokens：115 时间：2026-08-28 04:58:16

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5185 ms Tokens：115 时间：2026-08-28 04:58:23

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5832 ms Tokens：197 时间：2026-08-28 04:58:25

JSON

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

#33 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4252 ms Tokens：115 时间：2026-08-28 04:58:28

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"}

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：8309 ms Tokens：153 时间：2026-08-28 04:58:32

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：9996 ms Tokens：116 时间：2026-08-28 04:58:31

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1908 ms Tokens：136 时间：2026-08-28 04:58:41

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4049 ms Tokens：153 时间：2026-08-28 04:58:41

JSON

无输出内容。

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：4045 ms Tokens：130 时间：2026-08-28 04:58:43

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：219 ms Tokens：- 时间：2026-08-28 04:58:47

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：2475 ms Tokens：128 时间：2026-08-28 04:58:45

JSON

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

#41 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：219 ms Tokens：- 时间：2026-08-28 04:58:47

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：216 ms Tokens：- 时间：2026-08-28 04:58:47

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：4767 ms Tokens：158 时间：2026-08-28 04:58:47

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：4682 ms Tokens：169 时间：2026-08-28 04:58:47

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：4470 ms Tokens：177 时间：2026-08-28 04:58:52

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	731	200	113
DeepSeek-v4-pro-01	成功	1480	200	113
DeepSeek-v4-pro-01	成功	1262	200	113
DeepSeek-v4-pro-03	成功	1117	200	113
DeepSeek-v4-pro-03	成功	698	200	113
DeepSeek-v4-pro-03	成功	1622	200	113
DeepSeek-v4-pro-04	成功	920	200	113
DeepSeek-v4-pro-04	成功	724	200	113
DeepSeek-v4-pro-04	成功	1114	200	113
DeepSeek-v4-pro-02	成功	1117	200	113
DeepSeek-v4-pro-02	成功	1113	200	113
DeepSeek-v4-pro-02	成功	1147	200	113
jd-gemini-3.1-pro-preview	成功	2240	200	26
jd-gemini-3.1-pro-preview	成功	4739	200	252	{"status":"ok","message":"stable"}
jd-gemini-3.1-pro-preview	成功	2532	200	26
腾讯 Gemini 3.5 Flash	成功	4592	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	4522	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	3599	200	209	{"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash	成功	4568	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	3556	200	206	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	517	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	3646	200	209	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	547	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	488	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	526	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	499	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	505	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	4539	200	115
Kimi K3 - Aliyun Bailian	成功	2384	200	115
Kimi K3 - Aliyun Bailian	成功	8865	200	115
Kimi K3	成功	5185	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	5832	200	197	{"status":"ok","message":"stable"}
Kimi K3	成功	4252	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 - TopenRouter	成功	8309	200	153
Kimi K3 - TopenRouter	成功	9996	200	116
Qwen3.8-Max	成功	1908	200	136	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	4049	200	153
Qwen3.8-Max	成功	4045	200	130	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	219	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2475	200	128	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	219	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	216	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	4767	200	158	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4682	200	169	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4470	200	177	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细