Model Channel Lab

测试结果

Run ID: 20260829-123842-9828368d

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3339 ms

P95 / Tokens5453 / 4338

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	1005	1137	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1065	1188	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1163	1341	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1296	1668	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2011	2416	391
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2013	2792	345
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2884	3390	345
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	3239	3415	345
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4401	4636	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	5254	5453	485
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5348	8558	914
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	可用	10396	25555	79
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：1044 ms Tokens：113 时间：2026-08-29 12:37:38

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1177 ms Tokens：113 时间：2026-08-29 12:37:38

JSON

无输出内容。

#3 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1070 ms Tokens：113 时间：2026-08-29 12:37:39

JSON

无输出内容。

#4 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1668 ms Tokens：113 时间：2026-08-29 12:37:39

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1079 ms Tokens：113 时间：2026-08-29 12:37:40

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1341 ms Tokens：113 时间：2026-08-29 12:37:41

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1188 ms Tokens：113 时间：2026-08-29 12:37:41

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：830 ms Tokens：113 时间：2026-08-29 12:37:42

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1179 ms Tokens：113 时间：2026-08-29 12:37:43

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1016 ms Tokens：113 时间：2026-08-29 12:37:43

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：864 ms Tokens：113 时间：2026-08-29 12:37:44

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1137 ms Tokens：113 时间：2026-08-29 12:37:44

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：3470 ms Tokens：26 时间：2026-08-29 12:37:45

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：2164 ms Tokens：26 时间：2026-08-29 12:37:49

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：4193 ms Tokens：26 时间：2026-08-29 12:37:51

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

#16 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4374 ms Tokens：26 时间：2026-08-29 12:37:55

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4636 ms Tokens：26 时间：2026-08-29 12:37:59

JSON

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

模型：gemini-3.1-pro-preview 延迟：25555 ms Tokens：27 时间：2026-08-29 12:37:45

JSON

无输出内容。

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：8558 ms Tokens：499 时间：2026-08-29 12:38:04

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3810 ms Tokens：213 时间：2026-08-29 12:38:10

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：504 ms Tokens：- 时间：2026-08-29 12:38:14

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：521 ms Tokens：- 时间：2026-08-29 12:38:15

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：547 ms Tokens：- 时间：2026-08-29 12:38:15

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：433 ms Tokens：- 时间：2026-08-29 12:38:16

JSON

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

#25 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3677 ms Tokens：202 时间：2026-08-29 12:38:13

JSON

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

#26 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：424 ms Tokens：- 时间：2026-08-29 12:38:16

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：455 ms Tokens：- 时间：2026-08-29 12:38:16

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：2431 ms Tokens：115 时间：2026-08-29 12:38:17

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：3390 ms Tokens：115 时间：2026-08-29 12:38:16

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2831 ms Tokens：115 时间：2026-08-29 12:38:19

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：3415 ms Tokens：115 时间：2026-08-29 12:38:20

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：2952 ms Tokens：115 时间：2026-08-29 12:38:22

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1135 ms Tokens：115 时间：2026-08-29 12:38:25

JSON

{"status":"ok","message":"

#34 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：3351 ms Tokens：115 时间：2026-08-29 12:38:23

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"}

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2114 ms Tokens：115 时间：2026-08-29 12:38:27

JSON

{"status

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2792 ms Tokens：115 时间：2026-08-29 12:38:26

JSON

{"status":"

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1752 ms Tokens：127 时间：2026-08-29 12:38:29

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1865 ms Tokens：130 时间：2026-08-29 12:38:29

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：200 ms Tokens：- 时间：2026-08-29 12:38:31

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：221 ms Tokens：- 时间：2026-08-29 12:38:31

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：173 ms Tokens：- 时间：2026-08-29 12:38:31

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：2416 ms Tokens：134 时间：2026-08-29 12:38:31

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：5295 ms Tokens：161 时间：2026-08-29 12:38:31

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：5015 ms Tokens：164 时间：2026-08-29 12:38:33

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：5453 ms Tokens：160 时间：2026-08-29 12:38:37

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	1044	200	113
DeepSeek-v4-pro-01	成功	1177	200	113
DeepSeek-v4-pro-03	成功	1070	200	113
DeepSeek-v4-pro-01	成功	1668	200	113
DeepSeek-v4-pro-03	成功	1079	200	113
DeepSeek-v4-pro-03	成功	1341	200	113
DeepSeek-v4-pro-04	成功	1188	200	113
DeepSeek-v4-pro-04	成功	830	200	113
DeepSeek-v4-pro-04	成功	1179	200	113
DeepSeek-v4-pro-02	成功	1016	200	113
DeepSeek-v4-pro-02	成功	864	200	113
DeepSeek-v4-pro-02	成功	1137	200	113
jd-gemini-3.1-pro-preview	成功	3470	200	26
jd-gemini-3.1-pro-preview	成功	2164	200	26
腾讯 Gemini 3.5 Flash	成功	4193	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	4374	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	4636	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
jd-gemini-3.1-pro-preview	成功	25555	200	27
qwen3.6-plus	成功	8558	200	499	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	3810	200	213	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	504	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	521	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	547	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	433	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	3677	200	202	{"status":"ok","message":"stable"}
yuling-gpt-5.5	失败	424	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	455	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2431	200	115
Kimi K3 - Aliyun Bailian	成功	3390	200	115
Kimi K3 - Aliyun Bailian	成功	2831	200	115
Kimi K3	成功	3415	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	2952	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter	成功	1135	200	115	{"status":"ok","message":"
Kimi K3	成功	3351	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	2114	200	115	{"status
Kimi K3 - TopenRouter	成功	2792	200	115	{"status":"
Qwen3.8-Max	成功	1752	200	127	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1865	200	130	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	200	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	221	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	173	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2416	200	134	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5295	200	161	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5015	200	164	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5453	200	160	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细