Model Channel Lab

测试结果

Run ID: 20260828-111009-d759572a

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟6647 ms

P95 / Tokens7332 / 4153

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	982	1417	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1280	1552	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1326	1499	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1412	1800	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2042	2167	388
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2672	2959	78
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	稳定	4154	4507	711
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4366	4587	78
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	可用	4935	6331	345
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	5145	5912	345
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	6211	7004	467
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	可用	45239	120054	385
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：1312 ms Tokens：113 时间：2026-08-28 11:07:26

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1800 ms Tokens：113 时间：2026-08-28 11:07:26

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1125 ms Tokens：113 时间：2026-08-28 11:07:28

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1417 ms Tokens：113 时间：2026-08-28 11:07:28

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：782 ms Tokens：113 时间：2026-08-28 11:07:29

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：747 ms Tokens：113 时间：2026-08-28 11:07:30

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1257 ms Tokens：113 时间：2026-08-28 11:07:30

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1499 ms Tokens：113 时间：2026-08-28 11:07:30

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1222 ms Tokens：113 时间：2026-08-28 11:07:31

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1136 ms Tokens：113 时间：2026-08-28 11:07:32

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1153 ms Tokens：113 时间：2026-08-28 11:07:32

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1552 ms Tokens：113 时间：2026-08-28 11:07:33

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：2555 ms Tokens：26 时间：2026-08-28 11:07:33

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：2504 ms Tokens：26 时间：2026-08-28 11:07:35

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：2959 ms Tokens：26 时间：2026-08-28 11:07:36

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：4587 ms Tokens：26 时间：2026-08-28 11:07:37

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：4341 ms Tokens：26 时间：2026-08-28 11:07:39

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4170 ms Tokens：26 时间：2026-08-28 11:07:42

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4249 ms Tokens：243 时间：2026-08-28 11:07:43

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4507 ms Tokens：259 时间：2026-08-28 11:07:46

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：526 ms Tokens：- 时间：2026-08-28 11:07:50

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：3706 ms Tokens：209 时间：2026-08-28 11:07:47

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：486 ms Tokens：- 时间：2026-08-28 11:07:51

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：458 ms Tokens：- 时间：2026-08-28 11:07:51

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：536 ms Tokens：- 时间：2026-08-28 11:07:51

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：519 ms Tokens：- 时间：2026-08-28 11:07:52

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：460 ms Tokens：- 时间：2026-08-28 11:07:52

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：5887 ms Tokens：115 时间：2026-08-28 11:07:52

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：6331 ms Tokens：115 时间：2026-08-28 11:07:52

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2589 ms Tokens：115 时间：2026-08-28 11:07:58

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4715 ms Tokens：115 时间：2026-08-28 11:07:58

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：4808 ms Tokens：115 时间：2026-08-28 11:08:01

JSON

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

#33 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5912 ms Tokens：115 时间：2026-08-28 11:08:03

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"}

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：8332 ms Tokens：116 时间：2026-08-28 11:08:06

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：7332 ms Tokens：116 时间：2026-08-28 11:08:14

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1898 ms Tokens：129 时间：2026-08-28 11:08:21

JSON

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

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2167 ms Tokens：128 时间：2026-08-28 11:08:23

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2063 ms Tokens：131 时间：2026-08-28 11:08:25

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：210 ms Tokens：- 时间：2026-08-28 11:08:27

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：197 ms Tokens：- 时间：2026-08-28 11:08:28

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：223 ms Tokens：- 时间：2026-08-28 11:08:28

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：6628 ms Tokens：145 时间：2026-08-28 11:08:28

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：7004 ms Tokens：152 时间：2026-08-28 11:08:35

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：5001 ms Tokens：170 时间：2026-08-28 11:08:42

JSON

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

#45 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：120054 ms Tokens：153 时间：2026-08-28 11:08:09

JSON

无输出内容。

表格明细

渠道	状态	延迟 ms	HTTP	Tokens	输出 / 错误
DeepSeek-v4-pro-01	成功	1312	200	113
DeepSeek-v4-pro-01	成功	1800	200	113
DeepSeek-v4-pro-01	成功	1125	200	113
DeepSeek-v4-pro-03	成功	1417	200	113
DeepSeek-v4-pro-03	成功	782	200	113
DeepSeek-v4-pro-03	成功	747	200	113
DeepSeek-v4-pro-04	成功	1257	200	113
DeepSeek-v4-pro-04	成功	1499	200	113
DeepSeek-v4-pro-04	成功	1222	200	113
DeepSeek-v4-pro-02	成功	1136	200	113
DeepSeek-v4-pro-02	成功	1153	200	113
DeepSeek-v4-pro-02	成功	1552	200	113
jd-gemini-3.1-pro-preview	成功	2555	200	26
jd-gemini-3.1-pro-preview	成功	2504	200	26
jd-gemini-3.1-pro-preview	成功	2959	200	26
腾讯 Gemini 3.5 Flash	成功	4587	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	4341	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	4170	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	4249	200	243	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4507	200	259	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	526	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	3706	200	209	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	486	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	458	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	536	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	519	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	460	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	5887	200	115
Kimi K3 - Aliyun Bailian	成功	6331	200	115
Kimi K3 - Aliyun Bailian	成功	2589	200	115
Kimi K3	成功	4715	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	4808	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	5912	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 - TopenRouter	成功	8332	200	116
Kimi K3 - TopenRouter	成功	7332	200	116
Qwen3.8-Max	成功	1898	200	129	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2167	200	128	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2063	200	131	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	210	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	197	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	223	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high	成功	6628	200	145	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	7004	200	152	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5001	200	170	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	120054	200	153

历史详情

测试结果

结果明细

表格明细