历史详情

Run ID: 20260830-120252-d46cf821

返回历史

测试结果

Run ID: 20260830-120252-d46cf821

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3301 ms
P95 / Tokens8904 / 4725
渠道模型成功失败成功率失败率稳定性平均延迟 msP95 msTokens首个错误
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1252 1624 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1264 1740 459
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1283 1405 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1333 1477 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1503 1828 339
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2195 2385 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2406 2946 78
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2647 3466 396
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 4473 6906 750
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4581 5203 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 4836 5526 484
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 11839 16120 779
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:1278 ms Tokens:113 时间:2026-08-30 12:01:48
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1405 ms Tokens:113 时间:2026-08-30 12:01:48
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1373 ms Tokens:113 时间:2026-08-30 12:01:50
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1828 ms Tokens:113 时间:2026-08-30 12:01:50
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1151 ms Tokens:113 时间:2026-08-30 12:01:51
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1477 ms Tokens:113 时间:2026-08-30 12:01:52
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1262 ms Tokens:113 时间:2026-08-30 12:01:52
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1405 ms Tokens:113 时间:2026-08-30 12:01:53
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1183 ms Tokens:113 时间:2026-08-30 12:01:54
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1624 ms Tokens:113 时间:2026-08-30 12:01:54
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1348 ms Tokens:113 时间:2026-08-30 12:01:55
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:784 ms Tokens:113 时间:2026-08-30 12:01:56
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:2069 ms Tokens:26 时间:2026-08-30 12:01:57
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:2946 ms Tokens:26 时间:2026-08-30 12:01:56
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:2205 ms Tokens:26 时间:2026-08-30 12:01:59
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:4223 ms Tokens:26 时间:2026-08-30 12:01:59
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:5203 ms Tokens:26 时间:2026-08-30 12:02:01
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I
#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4319 ms Tokens:26 时间:2026-08-30 12:02:03
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
#19 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3066 ms Tokens:158 时间:2026-08-30 12:02:06
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3449 ms Tokens:193 时间:2026-08-30 12:02:09
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:524 ms Tokens:- 时间:2026-08-30 12:02:13
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:501 ms Tokens:- 时间:2026-08-30 12:02:13
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:523 ms Tokens:- 时间:2026-08-30 12:02:14
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:6906 ms Tokens:399 时间:2026-08-30 12:02:08
JSON
{"status":"ok","message":"stable"}
#25 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:536 ms Tokens:- 时间:2026-08-30 12:02:14
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:471 ms Tokens:- 时间:2026-08-30 12:02:15
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:530 ms Tokens:- 时间:2026-08-30 12:02:15
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:2255 ms Tokens:115 时间:2026-08-30 12:02:15
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2385 ms Tokens:115 时间:2026-08-30 12:02:15
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1945 ms Tokens:115 时间:2026-08-30 12:02:17
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:10495 ms Tokens:199 时间:2026-08-30 12:02:19
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:16120 ms Tokens:340 时间:2026-08-30 12:02:18
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1740 ms Tokens:153 时间:2026-08-30 12:02:34
JSON
无输出内容。
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1124 ms Tokens:153 时间:2026-08-30 12:02:36
JSON
无输出内容。
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:930 ms Tokens:153 时间:2026-08-30 12:02:37
JSON
无输出内容。
#36 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:8904 ms Tokens:240 时间:2026-08-30 12:02:30
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1913 ms Tokens:125 时间:2026-08-30 12:02:38
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2563 ms Tokens:145 时间:2026-08-30 12:02:39
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:195 ms Tokens:- 时间:2026-08-30 12:02:41
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:159 ms Tokens:- 时间:2026-08-30 12:02:41
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:193 ms Tokens:- 时间:2026-08-30 12:02:42
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:3466 ms Tokens:126 时间:2026-08-30 12:02:40
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:5526 ms Tokens:169 时间:2026-08-30 12:02:42
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:4432 ms Tokens:156 时间:2026-08-30 12:02:43
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:4550 ms Tokens:159 时间:2026-08-30 12:02:47
JSON
{"status":"ok","message":"stable"}

表格明细

渠道状态延迟 msHTTPTokens输出 / 错误
DeepSeek-v4-pro-01 成功 1278 200 113
DeepSeek-v4-pro-01 成功 1405 200 113
DeepSeek-v4-pro-03 成功 1373 200 113
DeepSeek-v4-pro-01 成功 1828 200 113
DeepSeek-v4-pro-03 成功 1151 200 113
DeepSeek-v4-pro-03 成功 1477 200 113
DeepSeek-v4-pro-04 成功 1262 200 113
DeepSeek-v4-pro-04 成功 1405 200 113
DeepSeek-v4-pro-04 成功 1183 200 113
DeepSeek-v4-pro-02 成功 1624 200 113
DeepSeek-v4-pro-02 成功 1348 200 113
DeepSeek-v4-pro-02 成功 784 200 113
jd-gemini-3.1-pro-preview 成功 2069 200 26
jd-gemini-3.1-pro-preview 成功 2946 200 26
jd-gemini-3.1-pro-preview 成功 2205 200 26
腾讯 Gemini 3.5 Flash 成功 4223 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 5203 200 26 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning_content": "**My Internal Monologue on Summarizing and the User's Expertise**\n\nAlright, let's break down this request. The core task is to summarize a piece of text, but the crucial constraints are:\n\n1. **First-Person Perspective:** I need to inhabit the *thoughts* described in the text, speaking as if they are my own internal musings. This isn't about me *reporting* on the thoughts; it's about me *having* them.\n2. **Fulsome Summary of Thought Process:** This means I can't just give a brief overview. I need to go deep into the *how* and *why* of the thinking, detailing the steps, the considerations, the nuances. It’s about laying bare the entire intellectual journey.\n3. **Target Audience is Expert:** The user is an expert. This implies I can skip over foundational explanations and assume a sophisticated understanding of the subject matter. I don't need to dumb anything down; in fact, I should probably use precise language and acknowledge the inherent complexities they'd expect.\n4. **Specific Starting Header:** The summary *must* begin with a bolded header, and the example given is \"My Summary:\". I
腾讯 Gemini 3.5 Flash 成功 4319 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 3066 200 158 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 3449 200 193 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 524 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 501 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 523 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 6906 200 399 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 536 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 471 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 530 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 2255 200 115
Kimi K3 - Aliyun Bailian 成功 2385 200 115
Kimi K3 - Aliyun Bailian 成功 1945 200 115
Kimi K3 成功 10495 200 199 {"status":"ok","message":"stable"}
Kimi K3 成功 16120 200 340 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1740 200 153
Kimi K3 - TopenRouter 成功 1124 200 153
Kimi K3 - TopenRouter 成功 930 200 153
Kimi K3 成功 8904 200 240 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1913 200 125 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2563 200 145 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 195 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 159 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 193 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 3466 200 126 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5526 200 169 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4432 200 156 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4550 200 159 {"status":"ok","message":"stable"}