Model Channel Lab

测试结果

Run ID: 20260828-005416-3f7b9f62

导出 JSON

总请求45

成功 / 失败36/9

成功率80.0%

平均延迟3396 ms

P95 / Tokens6986 / 4214

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	1119	1222	339
DeepSeek-v4-pro-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1152	1381	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1308	1509	339
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1396	1722	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2486	2763	426
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	3/3	0/3	100.0%	0.0%	稳定	2886	3270	78
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	3077	3921	345
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	稳定	3598	4614	189
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	4778	5722	758
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	可用	5763	7463	78
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	6532	6986	503
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	6656	8202	481
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：896 ms Tokens：113 时间：2026-08-28 00:53:10

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1381 ms Tokens：113 时间：2026-08-28 00:53:10

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1181 ms Tokens：113 时间：2026-08-28 00:53:11

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1305 ms Tokens：113 时间：2026-08-28 00:53:12

JSON

无输出内容。

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1112 ms Tokens：113 时间：2026-08-28 00:53:12

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1509 ms Tokens：113 时间：2026-08-28 00:53:13

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1222 ms Tokens：113 时间：2026-08-28 00:53:13

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1141 ms Tokens：113 时间：2026-08-28 00:53:14

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：995 ms Tokens：113 时间：2026-08-28 00:53:15

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1083 ms Tokens：113 时间：2026-08-28 00:53:16

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1722 ms Tokens：113 时间：2026-08-28 00:53:16

JSON

{"status":"

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1383 ms Tokens：113 时间：2026-08-28 00:53:17

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：3270 ms Tokens：26 时间：2026-08-28 00:53:17

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：3095 ms Tokens：26 时间：2026-08-28 00:53:18

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：2294 ms Tokens：26 时间：2026-08-28 00:53:21

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：5188 ms Tokens：26 时间：2026-08-28 00:53:21

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：4639 ms Tokens：26 时间：2026-08-28 00:53:23

JSON

#18 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5722 ms Tokens：331 时间：2026-08-28 00:53:28

JSON

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

#19 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：7463 ms Tokens：26 时间：2026-08-28 00:53:26

JSON

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：3704 ms Tokens：206 时间：2026-08-28 00:53:34

JSON

```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：530 ms Tokens：- 时间：2026-08-28 00:53:38

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：4909 ms Tokens：221 时间：2026-08-28 00:53:33

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：525 ms Tokens：- 时间：2026-08-28 00:53:38

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：525 ms Tokens：- 时间：2026-08-28 00:53:38

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：537 ms Tokens：- 时间：2026-08-28 00:53:39

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：536 ms Tokens：- 时间：2026-08-28 00:53:39

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：472 ms Tokens：- 时间：2026-08-28 00:53:39

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：2660 ms Tokens：115 时间：2026-08-28 00:53:40

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：3921 ms Tokens：115 时间：2026-08-28 00:53:39

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2650 ms Tokens：115 时间：2026-08-28 00:53:42

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5918 ms Tokens：115 时间：2026-08-28 00:53:45

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"}

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：8202 ms Tokens：251 时间：2026-08-28 00:53:43

JSON

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

#33 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：2930 ms Tokens：65 时间：2026-08-28 00:53:51

JSON

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

#34 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：5848 ms Tokens：115 时间：2026-08-28 00:53:51

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"}

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3252 ms Tokens：65 时间：2026-08-28 00:53:54

JSON

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

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2763 ms Tokens：152 时间：2026-08-28 00:53:58

JSON

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

#37 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4614 ms Tokens：59 时间：2026-08-28 00:53:57

JSON

{"status":"

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2360 ms Tokens：150 时间：2026-08-28 00:54:00

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：213 ms Tokens：- 时间：2026-08-28 00:54:03

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：233 ms Tokens：- 时间：2026-08-28 00:54:03

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：172 ms Tokens：- 时间：2026-08-28 00:54:03

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：2337 ms Tokens：124 时间：2026-08-28 00:54:01

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：6302 ms Tokens：171 时间：2026-08-28 00:54:03

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：6986 ms Tokens：167 时间：2026-08-28 00:54:04

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：6310 ms Tokens：165 时间：2026-08-28 00:54:10

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	896	200	113
DeepSeek-v4-pro-01	成功	1381	200	113
DeepSeek-v4-pro-01	成功	1181	200	113
DeepSeek-v4-pro-03	成功	1305	200	113
DeepSeek-v4-pro-03	成功	1112	200	113
DeepSeek-v4-pro-03	成功	1509	200	113
DeepSeek-v4-pro-04	成功	1222	200	113
DeepSeek-v4-pro-04	成功	1141	200	113
DeepSeek-v4-pro-04	成功	995	200	113
DeepSeek-v4-pro-02	成功	1083	200	113
DeepSeek-v4-pro-02	成功	1722	200	113	{"status":"
DeepSeek-v4-pro-02	成功	1383	200	113
jd-gemini-3.1-pro-preview	成功	3270	200	26
jd-gemini-3.1-pro-preview	成功	3095	200	26
jd-gemini-3.1-pro-preview	成功	2294	200	26
腾讯 Gemini 3.5 Flash	成功	5188	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	4639	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	5722	200	331	{"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash	成功	7463	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	3704	200	206	```json {"status":"ok","message":"stable"} ```
pixflow-gemini-3.1-pro-preview	失败	530	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus	成功	4909	200	221	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	525	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	525	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	537	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	472	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian	成功	2660	200	115
Kimi K3 - Aliyun Bailian	成功	3921	200	115
Kimi K3 - Aliyun Bailian	成功	2650	200	115
Kimi K3	成功	5918	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	成功	8202	200	251	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	2930	200	65	{"status":"ok","message":"stable"}
Kimi K3	成功	5848	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 - TopenRouter	成功	3252	200	65	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2763	200	152	{"status":"ok","message":"stable"}
Kimi K3 - TopenRouter	成功	4614	200	59	{"status":"
Qwen3.8-Max	成功	2360	200	150	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	213	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	233	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	172	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max	成功	2337	200	124	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6302	200	171	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6986	200	167	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	6310	200	165	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细