Model Channel Lab

测试结果

Run ID: 20260827-012349-c02ef1bb

导出 JSON

总请求45

成功 / 失败35/10

成功率77.78%

平均延迟4451 ms

P95 / Tokens12741 / 4180

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-01	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1074	1231	339
DeepSeek-v4-pro-03	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1172	1213	339
DeepSeek-v4-pro-04	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	稳定	1227	1438	339
Qwen3.8-Max	qwen3.8-max	3/3	0/3	100.0%	0.0%	稳定	2019	2190	384
Kimi K3 - Aliyun Bailian	kimi/kimi-k3	3/3	0/3	100.0%	0.0%	稳定	2350	2384	345
DeepSeek-v4-pro-02	deepseek-v4-pro	3/3	0/3	100.0%	0.0%	可用	2721	6263	339
腾讯 Gemini 3.5 Flash	gemini-3.5-flash	3/3	0/3	100.0%	0.0%	稳定	4435	4528	78
qwen3.6-plus	qwen3.6-plus	3/3	0/3	100.0%	0.0%	可用	4770	5804	791
yulin-gemini-3.7-flash-high	gemini-3.7-flash-high	3/3	0/3	100.0%	0.0%	可用	7668	12741	481
Kimi K3	kimi-k3	3/3	0/3	100.0%	0.0%	可用	9440	13738	345
Kimi K3 - TopenRouter	kimi-k3	3/3	0/3	100.0%	0.0%	可用	12664	30355	348
jd-gemini-3.1-pro-preview	gemini-3.1-pro-preview	2/3	1/3	66.67%	33.33%	不稳定	3582	4543	52	timeout: The read operation timed out
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：788 ms Tokens：113 时间：2026-08-27 01:22:13

JSON

无输出内容。

#2 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1205 ms Tokens：113 时间：2026-08-27 01:22:13

JSON

无输出内容。

#3 DeepSeek-v4-pro-01 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1231 ms Tokens：113 时间：2026-08-27 01:22:14

JSON

无输出内容。

#4 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1140 ms Tokens：113 时间：2026-08-27 01:22:15

JSON

{"status":"

#5 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1164 ms Tokens：113 时间：2026-08-27 01:22:15

JSON

无输出内容。

#6 DeepSeek-v4-pro-03 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1213 ms Tokens：113 时间：2026-08-27 01:22:16

JSON

无输出内容。

#7 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1438 ms Tokens：113 时间：2026-08-27 01:22:17

JSON

无输出内容。

#8 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1145 ms Tokens：113 时间：2026-08-27 01:22:17

JSON

无输出内容。

#9 DeepSeek-v4-pro-04 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1099 ms Tokens：113 时间：2026-08-27 01:22:18

JSON

无输出内容。

#10 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：1233 ms Tokens：113 时间：2026-08-27 01:22:19

JSON

无输出内容。

#11 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：668 ms Tokens：113 时间：2026-08-27 01:22:20

JSON

无输出内容。

#12 DeepSeek-v4-pro-02 成功 HTTP 200

模型：deepseek-v4-pro 延迟：6263 ms Tokens：113 时间：2026-08-27 01:22:18

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：4543 ms Tokens：26 时间：2026-08-27 01:22:21

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：2621 ms Tokens：26 时间：2026-08-27 01:22:24

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：4528 ms Tokens：26 时间：2026-08-27 01:22:27

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：4424 ms Tokens：26 时间：2026-08-27 01:22:31

JSON

#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200

模型：gemini-3.5-flash 延迟：4354 ms Tokens：26 时间：2026-08-27 01:22:36

JSON

#18 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：5804 ms Tokens：331 时间：2026-08-27 01:22:40

JSON

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

#19 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4330 ms Tokens：221 时间：2026-08-27 01:22:46

JSON

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

#20 qwen3.6-plus 成功 HTTP 200

模型：qwen3.6-plus 延迟：4177 ms Tokens：239 时间：2026-08-27 01:22:50

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：552 ms Tokens：- 时间：2026-08-27 01:22:55

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：548 ms Tokens：- 时间：2026-08-27 01:22:55

JSON

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

#23 jd-gemini-3.1-pro-preview 失败 HTTP -

模型：gemini-3.1-pro-preview 延迟：30186 ms Tokens：- 时间：2026-08-27 01:22:26

JSON

timeout: The read operation timed out

#24 yuling-gpt-5.5 失败 HTTP 403

模型：gpt-5.5 延迟：452 ms Tokens：- 时间：2026-08-27 01:22:56

JSON

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

#25 pixflow-gemini-3.1-pro-preview 失败 HTTP 403

模型：gemini-3.1-pro-preview 延迟：553 ms Tokens：- 时间：2026-08-27 01:22:56

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：510 ms Tokens：- 时间：2026-08-27 01:22:56

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：487 ms Tokens：- 时间：2026-08-27 01:22:56

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：2299 ms Tokens：115 时间：2026-08-27 01:22:57

JSON

无输出内容。

#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2367 ms Tokens：115 时间：2026-08-27 01:22:57

JSON

无输出内容。

#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200

模型：kimi/kimi-k3 延迟：2384 ms Tokens：115 时间：2026-08-27 01:22:59

JSON

无输出内容。

#31 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：7706 ms Tokens：115 时间：2026-08-27 01:22:59

JSON

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

#32 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：6878 ms Tokens：115 时间：2026-08-27 01:23:01

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"}

#33 Kimi K3 成功 HTTP 200

模型：kimi-k3 延迟：13738 ms Tokens：115 时间：2026-08-27 01:23:07

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"}

#34 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：3277 ms Tokens：116 时间：2026-08-27 01:23:20

JSON

无输出内容。

#35 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：4362 ms Tokens：116 时间：2026-08-27 01:23:24

JSON

无输出内容。

#36 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2050 ms Tokens：127 时间：2026-08-27 01:23:28

JSON

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

#37 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：1817 ms Tokens：122 时间：2026-08-27 01:23:30

JSON

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

#38 Qwen3.8-Max 成功 HTTP 200

模型：qwen3.8-max 延迟：2190 ms Tokens：135 时间：2026-08-27 01:23:32

JSON

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

#39 MiniMax H3 Context IR 失败 HTTP 400

模型：MiniMax-H3 延迟：204 ms Tokens：- 时间：2026-08-27 01:23:34

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：211 ms Tokens：- 时间：2026-08-27 01:23:34

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：134 ms Tokens：- 时间：2026-08-27 01:23:35

JSON

HTTP 400: binding: expr_path=content, cause=missing required parameter

#42 Kimi K3 - TopenRouter 成功 HTTP 200

模型：kimi-k3 延迟：30355 ms Tokens：116 时间：2026-08-27 01:23:08

JSON

无输出内容。

#43 yulin-gemini-3.7-flash-high 成功 HTTP 200

模型：gemini-3.7-flash-high 延迟：5182 ms Tokens：150 时间：2026-08-27 01:23:39

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：12741 ms Tokens：161 时间：2026-08-27 01:23:35

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：5081 ms Tokens：170 时间：2026-08-27 01:23:44

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	788	200	113
DeepSeek-v4-pro-01	成功	1205	200	113
DeepSeek-v4-pro-01	成功	1231	200	113
DeepSeek-v4-pro-03	成功	1140	200	113	{"status":"
DeepSeek-v4-pro-03	成功	1164	200	113
DeepSeek-v4-pro-03	成功	1213	200	113
DeepSeek-v4-pro-04	成功	1438	200	113
DeepSeek-v4-pro-04	成功	1145	200	113
DeepSeek-v4-pro-04	成功	1099	200	113
DeepSeek-v4-pro-02	成功	1233	200	113
DeepSeek-v4-pro-02	成功	668	200	113
DeepSeek-v4-pro-02	成功	6263	200	113
jd-gemini-3.1-pro-preview	成功	4543	200	26
jd-gemini-3.1-pro-preview	成功	2621	200	26
腾讯 Gemini 3.5 Flash	成功	4528	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	4424	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	4354	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	5804	200	331	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4330	200	221	{"status":"ok","message":"stable"}
qwen3.6-plus	成功	4177	200	239	{"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview	失败	552	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	548	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
jd-gemini-3.1-pro-preview	失败	30186	-	-	timeout: The read operation timed out
yuling-gpt-5.5	失败	452	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview	失败	553	403	-	HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5	失败	510	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"}
Kimi K3 - Aliyun Bailian	成功	2299	200	115
Kimi K3 - Aliyun Bailian	成功	2367	200	115
Kimi K3 - Aliyun Bailian	成功	2384	200	115
Kimi K3	成功	7706	200	115	{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3	成功	6878	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	成功	13738	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 - TopenRouter	成功	3277	200	116
Kimi K3 - TopenRouter	成功	4362	200	116
Qwen3.8-Max	成功	2050	200	127	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	1817	200	122	{"status":"ok","message":"stable"}
Qwen3.8-Max	成功	2190	200	135	{"status":"ok","message":"stable"}
MiniMax H3 Context IR	失败	204	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	211	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR	失败	134	400	-	HTTP 400: binding: expr_path=content, cause=missing required parameter
Kimi K3 - TopenRouter	成功	30355	200	116
yulin-gemini-3.7-flash-high	成功	5182	200	150	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	12741	200	161	{"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high	成功	5081	200	170	{"status":"ok","message":"stable"}

历史详情

测试结果

结果明细

表格明细