历史详情

Run ID: 20260828-181852-edcccd88

返回历史

测试结果

Run ID: 20260828-181852-edcccd88

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3579 ms
P95 / Tokens8974 / 4406
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-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1210 1689 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1241 1473 339
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1304 1565 459
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1351 1712 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1376 1548 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2034 2203 381
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 稳定 4066 4408 692
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 可用 4384 7933 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 稳定 4617 4774 507
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 6293 8052 78
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 7439 9023 510
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 可用 7633 9844 345
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:872 ms Tokens:113 时间:2026-08-28 18:17:43
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1071 ms Tokens:113 时间:2026-08-28 18:17:43
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1208 ms Tokens:113 时间:2026-08-28 18:17:44
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1689 ms Tokens:113 时间:2026-08-28 18:17:44
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1135 ms Tokens:113 时间:2026-08-28 18:17:46
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1712 ms Tokens:113 时间:2026-08-28 18:17:46
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1473 ms Tokens:113 时间:2026-08-28 18:17:47
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1113 ms Tokens:113 时间:2026-08-28 18:17:48
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1137 ms Tokens:113 时间:2026-08-28 18:17:48
JSON
{"status":"
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1455 ms Tokens:113 时间:2026-08-28 18:17:49
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1126 ms Tokens:113 时间:2026-08-28 18:17:49
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1548 ms Tokens:113 时间:2026-08-28 18:17:50
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:2448 ms Tokens:26 时间:2026-08-28 18:17:51
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:2771 ms Tokens:26 时间:2026-08-28 18:17:52
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:7933 ms Tokens:26 时间:2026-08-28 18:17:53
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:8052 ms Tokens:26 时间:2026-08-28 18:17:55
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4271 ms Tokens:26 时间:2026-08-28 18:18:03
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
#18 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:6557 ms Tokens:26 时间:2026-08-28 18:18:01
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
#19 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3596 ms Tokens:206 时间:2026-08-28 18:18:07
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4408 ms Tokens:243 时间:2026-08-28 18:18:07
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:531 ms Tokens:- 时间:2026-08-28 18:18:11
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:530 ms Tokens:- 时间:2026-08-28 18:18:12
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:531 ms Tokens:- 时间:2026-08-28 18:18:12
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:452 ms Tokens:- 时间:2026-08-28 18:18:13
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:481 ms Tokens:- 时间:2026-08-28 18:18:13
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:450 ms Tokens:- 时间:2026-08-28 18:18:14
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:4196 ms Tokens:243 时间:2026-08-28 18:18:11
JSON
{"status":"ok","message":"stable"}
#28 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:9844 ms Tokens:115 时间:2026-08-28 18:18:14
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:8974 ms Tokens:115 时间:2026-08-28 18:18:15
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:4082 ms Tokens:115 时间:2026-08-28 18:18:24
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5912 ms Tokens:115 时间:2026-08-28 18:18:24
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:9023 ms Tokens:191 时间:2026-08-28 18:18:28
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:7383 ms Tokens:204 时间:2026-08-28 18:18:30
JSON
{"status":"ok","message":"stable"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1328 ms Tokens:153 时间:2026-08-28 18:18:37
JSON
无输出内容。
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1021 ms Tokens:153 时间:2026-08-28 18:18:38
JSON
无输出内容。
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:1565 ms Tokens:153 时间:2026-08-28 18:18:39
JSON
无输出内容。
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1923 ms Tokens:128 时间:2026-08-28 18:18:39
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2203 ms Tokens:125 时间:2026-08-28 18:18:40
JSON
{"status":"ok","message":"stable"}
#39 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1978 ms Tokens:128 时间:2026-08-28 18:18:40
JSON
{"status":"ok","message":"stable"}
#40 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:180 ms Tokens:- 时间:2026-08-28 18:18:42
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:222 ms Tokens:- 时间:2026-08-28 18:18:42
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:197 ms Tokens:- 时间:2026-08-28 18:18:42
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#43 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:4447 ms Tokens:162 时间:2026-08-28 18:18:43
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:4630 ms Tokens:159 时间:2026-08-28 18:18:43
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:4774 ms Tokens:186 时间:2026-08-28 18:18:47
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 872 200 113
DeepSeek-v4-pro-01 成功 1071 200 113
DeepSeek-v4-pro-03 成功 1208 200 113
DeepSeek-v4-pro-01 成功 1689 200 113
DeepSeek-v4-pro-03 成功 1135 200 113
DeepSeek-v4-pro-03 成功 1712 200 113
DeepSeek-v4-pro-04 成功 1473 200 113
DeepSeek-v4-pro-04 成功 1113 200 113
DeepSeek-v4-pro-04 成功 1137 200 113 {"status":"
DeepSeek-v4-pro-02 成功 1455 200 113
DeepSeek-v4-pro-02 成功 1126 200 113
DeepSeek-v4-pro-02 成功 1548 200 113
jd-gemini-3.1-pro-preview 成功 2448 200 26
jd-gemini-3.1-pro-preview 成功 2771 200 26
jd-gemini-3.1-pro-preview 成功 7933 200 26
腾讯 Gemini 3.5 Flash 成功 8052 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 4271 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 6557 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
qwen3.6-plus 成功 3596 200 206 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 4408 200 243 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 531 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 530 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 531 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 452 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 481 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 450 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 4196 200 243 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 9844 200 115
Kimi K3 - Aliyun Bailian 成功 8974 200 115
Kimi K3 - Aliyun Bailian 成功 4082 200 115
Kimi K3 成功 5912 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 9023 200 191 {"status":"ok","message":"stable"}
Kimi K3 成功 7383 200 204 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 1328 200 153
Kimi K3 - TopenRouter 成功 1021 200 153
Kimi K3 - TopenRouter 成功 1565 200 153
Qwen3.8-Max 成功 1923 200 128 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2203 200 125 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1978 200 128 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 180 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 222 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 197 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 4447 200 162 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4630 200 159 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 4774 200 186 {"status":"ok","message":"stable"}