Model Channel Lab

测试结果

Run ID: 20260830-055645-237a6c76

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟2637 ms

P95 / Tokens5574 / 4675

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	1061	1393	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1075	1694	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1239	1285	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1342	1502	339
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1449	1560	459
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	1970	3176	345
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2134	2304	390
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2222	2427	78
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4282	4321	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	稳定	4427	4777	524
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	4729	5574	522
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	5721	6215	923
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：1162 ms Tokens：113 时间：2026-08-30 05:55:54

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1271 ms Tokens：113 时间：2026-08-30 05:55:54

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1285 ms Tokens：113 时间：2026-08-30 05:55:55

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1393 ms Tokens：113 时间：2026-08-30 05:55:55

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：2026-08-30 05:55:56

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1093 ms Tokens：113 时间：2026-08-30 05:55:56

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1276 ms Tokens：113 时间：2026-08-30 05:55:57

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1250 ms Tokens：113 时间：2026-08-30 05:55:57

JSON

无输出内容。

#9 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：845 ms Tokens：113 时间：2026-08-30 05:55:58

JSON

无输出内容。

#10 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1502 ms Tokens：113 时间：2026-08-30 05:55:58

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：687 ms Tokens：113 时间：2026-08-30 05:55:59

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1694 ms Tokens：113 时间：2026-08-30 05:56:00

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：2210 ms Tokens：26 时间：2026-08-30 05:56:00

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：2427 ms Tokens：26 时间：2026-08-30 05:56:01

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：2031 ms Tokens：26 时间：2026-08-30 05:56:02

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：4254 ms Tokens：26 时间：2026-08-30 05:56:04

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：4272 ms Tokens：26 时间：2026-08-30 05:56:04

JSON

#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4321 ms Tokens：26 时间：2026-08-30 05:56:08

JSON

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：6215 ms Tokens：324 时间：2026-08-30 05:56:08

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4963 ms Tokens：275 时间：2026-08-30 05:56:12

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：544 ms Tokens：- 时间：2026-08-30 05:56:17

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：529 ms Tokens：- 时间：2026-08-30 05:56:18

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：459 ms Tokens：- 时间：2026-08-30 05:56:18

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：518 ms Tokens：- 时间：2026-08-30 05:56:19

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：440 ms Tokens：- 时间：2026-08-30 05:56:19

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：477 ms Tokens：- 时间：2026-08-30 05:56:20

JSON

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

#27 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5986 ms Tokens：324 时间：2026-08-30 05:56:15

JSON

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

#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1630 ms Tokens：115 时间：2026-08-30 05:56:21

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：1105 ms Tokens：115 时间：2026-08-30 05:56:22

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：3176 ms Tokens：115 时间：2026-08-30 05:56:20

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4318 ms Tokens：155 时间：2026-08-30 05:56:24

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5574 ms Tokens：203 时间：2026-08-30 05:56:23

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1560 ms Tokens：153 时间：2026-08-30 05:56:29

JSON

无输出内容。

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1516 ms Tokens：153 时间：2026-08-30 05:56:30

JSON

无输出内容。

#35 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：4295 ms Tokens：164 时间：2026-08-30 05:56:28

JSON

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

#36 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：1272 ms Tokens：153 时间：2026-08-30 05:56:32

JSON

无输出内容。

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1945 ms Tokens：130 时间：2026-08-30 05:56:32

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2304 ms Tokens：135 时间：2026-08-30 05:56:33

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：2026-08-30 05:56:36

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：179 ms Tokens：- 时间：2026-08-30 05:56:36

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：238 ms Tokens：- 时间：2026-08-30 05:56:36

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：2153 ms Tokens：125 时间：2026-08-30 05:56:34

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：4581 ms Tokens：165 时间：2026-08-30 05:56:36

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：4777 ms Tokens：189 时间：2026-08-30 05:56:36

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：3925 ms Tokens：170 时间：2026-08-30 05:56:41

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	1162	200	113
DeepSeek-v4-pro-01	成功	1271	200	113
DeepSeek-v4-pro-01	成功	1285	200	113
DeepSeek-v4-pro-03	成功	1393	200	113
DeepSeek-v4-pro-03	成功	698	200	113
DeepSeek-v4-pro-03	成功	1093	200	113
DeepSeek-v4-pro-04	成功	1276	200	113
DeepSeek-v4-pro-04	成功	1250	200	113
DeepSeek-v4-pro-02	成功	845	200	113
DeepSeek-v4-pro-04	成功	1502	200	113
DeepSeek-v4-pro-02	成功	687	200	113
DeepSeek-v4-pro-02	成功	1694	200	113
jd-gemini-3.1-pro-preview	成功	2210	200	26
jd-gemini-3.1-pro-preview	成功	2427	200	26
jd-gemini-3.1-pro-preview	成功	2031	200	26
腾讯 Gemini 3.5 Flash	成功	4254	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	4272	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	4321	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	6215	200	324	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4963	200	275	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	544	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"}
pixflow-gemini-3.1-pro-preview	失败	459	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	518	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	440	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	477	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	5986	200	324	{"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian	成功	1630	200	115
Kimi K3 - Aliyun Bailian	成功	1105	200	115
Kimi K3 - Aliyun Bailian	成功	3176	200	115
Kimi K3	成功	4318	200	155	{"status":"ok","message":"stable"}
Kimi K3	成功	5574	200	203	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1560	200	153
Kimi K3 - TopenRouter	成功	1516	200	153
Kimi K3	成功	4295	200	164	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	1272	200	153
Qwen3.8-Max	成功	1945	200	130	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2304	200	135	{"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	179	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	238	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2153	200	125	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4581	200	165	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	4777	200	189	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	3925	200	170	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细