历史详情

Run ID: 20260828-080342-e7aca1c7

返回历史

测试结果

Run ID: 20260828-080342-e7aca1c7

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3654 ms
P95 / Tokens10610 / 4418
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-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 996 1111 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1044 1164 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1150 1461 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1258 1340 339
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 1685 2673 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2304 2535 78
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2348 2952 384
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 5093 8393 348
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5576 6468 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 5755 7972 484
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5795 8466 1000
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 10853 11074 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:1207 ms Tokens:113 时间:2026-08-28 08:02:34
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1228 ms Tokens:113 时间:2026-08-28 08:02:34
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1111 ms Tokens:113 时间:2026-08-28 08:02:35
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1340 ms Tokens:113 时间:2026-08-28 08:02:35
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:815 ms Tokens:113 时间:2026-08-28 08:02:36
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1063 ms Tokens:113 时间:2026-08-28 08:02:36
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:938 ms Tokens:113 时间:2026-08-28 08:02:37
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1461 ms Tokens:113 时间:2026-08-28 08:02:37
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1052 ms Tokens:113 时间:2026-08-28 08:02:38
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1010 ms Tokens:113 时间:2026-08-28 08:02:39
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:959 ms Tokens:113 时间:2026-08-28 08:02:39
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1164 ms Tokens:113 时间:2026-08-28 08:02:40
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:2535 ms Tokens:26 时间:2026-08-28 08:02:40
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:2003 ms Tokens:26 时间:2026-08-28 08:02:41
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:2374 ms Tokens:26 时间:2026-08-28 08:02:42
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:5888 ms Tokens:26 时间:2026-08-28 08:02:43
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:6468 ms Tokens:26 时间:2026-08-28 08:02:45
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:4372 ms Tokens:26 时间:2026-08-28 08:02:49
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:4681 ms Tokens:267 时间:2026-08-28 08:02:51
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4238 ms Tokens:243 时间:2026-08-28 08:02:56
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:517 ms Tokens:- 时间:2026-08-28 08:03:00
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:533 ms Tokens:- 时间:2026-08-28 08:03:01
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:522 ms Tokens:- 时间:2026-08-28 08:03:01
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:8466 ms Tokens:490 时间:2026-08-28 08:02:53
JSON
{"status":"ok","message":"stable"}
#25 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:523 ms Tokens:- 时间:2026-08-28 08:03:02
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:543 ms Tokens:- 时间:2026-08-28 08:03:02
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:519 ms Tokens:- 时间:2026-08-28 08:03:02
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:1309 ms Tokens:115 时间:2026-08-28 08:03:03
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2673 ms Tokens:115 时间:2026-08-28 08:03:02
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:1075 ms Tokens:115 时间:2026-08-28 08:03:04
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:10610 ms Tokens:115 时间:2026-08-28 08:03:05
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:10876 ms Tokens:115 时间:2026-08-28 08:03:05
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
#33 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:8393 ms Tokens:116 时间:2026-08-28 08:03:16
JSON
无输出内容。
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:2602 ms Tokens:116 时间:2026-08-28 08:03:24
JSON
无输出内容。
#35 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:11074 ms Tokens:115 时间:2026-08-28 08:03:16
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "用户要求只回复 JSON:{\"status\":\"ok\",\"message\":\"stable\"}。"}, "logprobs": null, "finish_reason": "length"}
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1947 ms Tokens:126 时间:2026-08-28 08:03:27
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:4285 ms Tokens:116 时间:2026-08-28 08:03:27
JSON
无输出内容。
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2952 ms Tokens:130 时间:2026-08-28 08:03:29
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:217 ms Tokens:- 时间:2026-08-28 08:03:32
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:190 ms Tokens:- 时间:2026-08-28 08:03:32
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:201 ms Tokens:- 时间:2026-08-28 08:03:32
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:2145 ms Tokens:128 时间:2026-08-28 08:03:31
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:5333 ms Tokens:170 时间:2026-08-28 08:03:32
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:7972 ms Tokens:158 时间:2026-08-28 08:03:33
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:3960 ms Tokens:156 时间:2026-08-28 08:03:38
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 1207 200 113
DeepSeek-v4-pro-01 成功 1228 200 113
DeepSeek-v4-pro-03 成功 1111 200 113
DeepSeek-v4-pro-01 成功 1340 200 113
DeepSeek-v4-pro-03 成功 815 200 113
DeepSeek-v4-pro-03 成功 1063 200 113
DeepSeek-v4-pro-04 成功 938 200 113
DeepSeek-v4-pro-04 成功 1461 200 113
DeepSeek-v4-pro-04 成功 1052 200 113
DeepSeek-v4-pro-02 成功 1010 200 113
DeepSeek-v4-pro-02 成功 959 200 113
DeepSeek-v4-pro-02 成功 1164 200 113
jd-gemini-3.1-pro-preview 成功 2535 200 26
jd-gemini-3.1-pro-preview 成功 2003 200 26
jd-gemini-3.1-pro-preview 成功 2374 200 26
腾讯 Gemini 3.5 Flash 成功 5888 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 6468 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 4372 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 4681 200 267 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 4238 200 243 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 517 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 533 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 522 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 8466 200 490 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 523 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 543 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 519 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 1309 200 115
Kimi K3 - Aliyun Bailian 成功 2673 200 115
Kimi K3 - Aliyun Bailian 成功 1075 200 115
Kimi K3 成功 10610 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 10876 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 8393 200 116
Kimi K3 - TopenRouter 成功 2602 200 116
Kimi K3 成功 11074 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "用户要求只回复 JSON:{\"status\":\"ok\",\"message\":\"stable\"}。"}, "logprobs": null, "finish_reason": "length"}
Qwen3.8-Max 成功 1947 200 126 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 4285 200 116
Qwen3.8-Max 成功 2952 200 130 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 217 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 190 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 201 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
Qwen3.8-Max 成功 2145 200 128 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5333 200 170 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 7972 200 158 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3960 200 156 {"status":"ok","message":"stable"}