Model Channel Lab

测试结果

Run ID: 20260831-021717-6d3cdf70

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟2994 ms

P95 / Tokens6131 / 4423

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-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1117	1179	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1129	1187	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1180	1194	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1231	1489	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2183	2845	383
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2268	2353	345
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2542	2798	78
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	3393	4671	388
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	4260	5943	735
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4417	4572	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5204	6131	515
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	7010	8390	545
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：1170 ms Tokens：113 时间：2026-08-31 02:16:19

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1194 ms Tokens：113 时间：2026-08-31 02:16:19

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1178 ms Tokens：113 时间：2026-08-31 02:16:20

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1181 ms Tokens：113 时间：2026-08-31 02:16:20

JSON

{"status

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1020 ms Tokens：113 时间：2026-08-31 02:16:21

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1187 ms Tokens：113 时间：2026-08-31 02:16:21

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1033 ms Tokens：113 时间：2026-08-31 02:16:22

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1171 ms Tokens：113 时间：2026-08-31 02:16:22

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1489 ms Tokens：113 时间：2026-08-31 02:16:23

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1179 ms Tokens：113 时间：2026-08-31 02:16:24

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1065 ms Tokens：113 时间：2026-08-31 02:16:25

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1108 ms Tokens：113 时间：2026-08-31 02:16:25

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：2490 ms Tokens：26 时间：2026-08-31 02:16:26

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：2798 ms Tokens：26 时间：2026-08-31 02:16:26

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：2340 ms Tokens：26 时间：2026-08-31 02:16:28

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：4391 ms Tokens：26 时间：2026-08-31 02:16:29

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：4289 ms Tokens：26 时间：2026-08-31 02:16:31

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4572 ms Tokens：26 时间：2026-08-31 02:16:33

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3332 ms Tokens：189 时间：2026-08-31 02:16:35

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3507 ms Tokens：202 时间：2026-08-31 02:16:38

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：533 ms Tokens：- 时间：2026-08-31 02:16:41

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：528 ms Tokens：- 时间：2026-08-31 02:16:42

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：529 ms Tokens：- 时间：2026-08-31 02:16:42

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：487 ms Tokens：- 时间：2026-08-31 02:16:43

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：531 ms Tokens：- 时间：2026-08-31 02:16:43

JSON

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

#26 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5943 ms Tokens：344 时间：2026-08-31 02:16:38

JSON

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

#27 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：487 ms Tokens：- 时间：2026-08-31 02:16:44

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：2300 ms Tokens：115 时间：2026-08-31 02:16:44

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2353 ms Tokens：115 时间：2026-08-31 02:16:44

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2153 ms Tokens：115 时间：2026-08-31 02:16:47

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：8390 ms Tokens：206 时间：2026-08-31 02:16:47

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：7790 ms Tokens：162 时间：2026-08-31 02:16:49

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1131 ms Tokens：153 时间：2026-08-31 02:16:56

JSON

无输出内容。

#34 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4852 ms Tokens：177 时间：2026-08-31 02:16:55

JSON

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

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2575 ms Tokens：115 时间：2026-08-31 02:16:58

JSON

{"status

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2845 ms Tokens：115 时间：2026-08-31 02:17:00

JSON

无输出内容。

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：4671 ms Tokens：129 时间：2026-08-31 02:17:00

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：3142 ms Tokens：133 时间：2026-08-31 02:17:03

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：215 ms Tokens：- 时间：2026-08-31 02:17:06

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：199 ms Tokens：- 时间：2026-08-31 02:17:06

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：165 ms Tokens：- 时间：2026-08-31 02:17:06

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：2367 ms Tokens：126 时间：2026-08-31 02:17:05

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：4810 ms Tokens：162 时间：2026-08-31 02:17:07

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：6131 ms Tokens：180 时间：2026-08-31 02:17:06

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：4671 ms Tokens：173 时间：2026-08-31 02:17:12

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	1170	200	113
DeepSeek-v4-pro-01	成功	1194	200	113
DeepSeek-v4-pro-01	成功	1178	200	113
DeepSeek-v4-pro-03	成功	1181	200	113	{"status
DeepSeek-v4-pro-03	成功	1020	200	113
DeepSeek-v4-pro-03	成功	1187	200	113
DeepSeek-v4-pro-04	成功	1033	200	113
DeepSeek-v4-pro-04	成功	1171	200	113
DeepSeek-v4-pro-04	成功	1489	200	113
DeepSeek-v4-pro-02	成功	1179	200	113
DeepSeek-v4-pro-02	成功	1065	200	113
DeepSeek-v4-pro-02	成功	1108	200	113
jd-gemini-3.1-pro-preview	成功	2490	200	26
jd-gemini-3.1-pro-preview	成功	2798	200	26
jd-gemini-3.1-pro-preview	成功	2340	200	26
腾讯 Gemini 3.5 Flash	成功	4391	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	4289	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	4572	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	3332	200	189	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3507	200	202	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	533	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	528	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	529	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	487	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	531	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	5943	200	344	{"status":"ok","message":"stable"}
yuling-gpt-5.5	失败	487	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2300	200	115
Kimi K3 - Aliyun Bailian	成功	2353	200	115
Kimi K3 - Aliyun Bailian	成功	2153	200	115
Kimi K3	成功	8390	200	206	{"status":"ok","message":"stable"}
Kimi K3	成功	7790	200	162	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1131	200	153
Kimi K3	成功	4852	200	177	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2575	200	115	{"status
Kimi K3 - TopenRouter	成功	2845	200	115
Qwen3.8-Max	成功	4671	200	129	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	3142	200	133	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	215	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
MiniMax H3 Context IR	失败	165	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2367	200	126	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4810	200	162	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6131	200	180	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4671	200	173	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细