历史详情

Run ID: 20260828-151507-e1c24264

返回历史

测试结果

Run ID: 20260828-151507-e1c24264

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟4278 ms
P95 / Tokens7901 / 4247
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 1011 1197 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1203 1297 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1229 1349 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1310 1513 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2572 2951 393
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 稳定 4035 4718 644
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 4982 5162 78
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 可用 5115 8102 345
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5603 6625 430
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 6168 7901 433
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 6253 6383 516
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 2/3 1/3 66.67% 33.33% 不稳定 15644 28161 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:817 ms Tokens:113 时间:2026-08-28 15:13:34
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1197 ms Tokens:113 时间:2026-08-28 15:13:34
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1019 ms Tokens:113 时间:2026-08-28 15:13:35
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1085 ms Tokens:113 时间:2026-08-28 15:13:35
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1513 ms Tokens:113 时间:2026-08-28 15:13:36
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1332 ms Tokens:113 时间:2026-08-28 15:13:36
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1102 ms Tokens:113 时间:2026-08-28 15:13:37
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1210 ms Tokens:113 时间:2026-08-28 15:13:37
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1297 ms Tokens:113 时间:2026-08-28 15:13:38
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1212 ms Tokens:113 时间:2026-08-28 15:13:39
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1349 ms Tokens:113 时间:2026-08-28 15:13:40
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1128 ms Tokens:113 时间:2026-08-28 15:13:40
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:3127 ms Tokens:26 时间:2026-08-28 15:13:41
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:28161 ms Tokens:26 时间:2026-08-28 15:13:41
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:5077 ms Tokens:26 时间:2026-08-28 15:14:09
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
#16 jd-gemini-3.1-pro-preview 失败 HTTP -
模型:gemini-3.1-pro-preview 延迟:30214 ms Tokens:- 时间:2026-08-28 15:13:44
JSON
timeout: The read operation timed out
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:4709 ms Tokens:26 时间:2026-08-28 15:14:14
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:5162 ms Tokens:26 时间:2026-08-28 15:14:14
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:3661 ms Tokens:188 时间:2026-08-28 15:14:19
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:4718 ms Tokens:264 时间:2026-08-28 15:14:19
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:558 ms Tokens:- 时间:2026-08-28 15:14:24
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 15:14:24
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:539 ms Tokens:- 时间:2026-08-28 15:14:25
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:464 ms Tokens:- 时间:2026-08-28 15:14:25
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:514 ms Tokens:- 时间:2026-08-28 15:14:26
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#26 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:3726 ms Tokens:192 时间:2026-08-28 15:14:23
JSON
{"status":"ok","message":"stable"}
#27 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:447 ms Tokens:- 时间:2026-08-28 15:14:26
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:4519 ms Tokens:115 时间:2026-08-28 15:14:27
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2724 ms Tokens:115 时间:2026-08-28 15:14:31
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:8102 ms Tokens:115 时间:2026-08-28 15:14:27
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6625 ms Tokens:200 时间:2026-08-28 15:14:34
JSON
{"status":"ok","message":"stable"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5661 ms Tokens:115 时间:2026-08-28 15:14:35
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:4523 ms Tokens:115 时间:2026-08-28 15:14:41
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:6282 ms Tokens:140 时间:2026-08-28 15:14:41
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:6095 ms Tokens:193 时间:2026-08-28 15:14:45
JSON
{"status":"ok","message":"stable"}
#36 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:6383 ms Tokens:183 时间:2026-08-28 15:14:47
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2303 ms Tokens:138 时间:2026-08-28 15:14:51
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2462 ms Tokens:128 时间:2026-08-28 15:14:53
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:219 ms Tokens:- 时间:2026-08-28 15:14:56
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:154 ms Tokens:- 时间:2026-08-28 15:14:56
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:190 ms Tokens:- 时间:2026-08-28 15:14:56
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:2951 ms Tokens:127 时间:2026-08-28 15:14:54
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:5591 ms Tokens:145 时间:2026-08-28 15:14:56
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:7901 ms Tokens:152 时间:2026-08-28 15:14:56
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:5013 ms Tokens:136 时间:2026-08-28 15:15:02
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 817 200 113
DeepSeek-v4-pro-01 成功 1197 200 113
DeepSeek-v4-pro-01 成功 1019 200 113
DeepSeek-v4-pro-03 成功 1085 200 113
DeepSeek-v4-pro-03 成功 1513 200 113
DeepSeek-v4-pro-03 成功 1332 200 113
DeepSeek-v4-pro-04 成功 1102 200 113
DeepSeek-v4-pro-04 成功 1210 200 113
DeepSeek-v4-pro-04 成功 1297 200 113
DeepSeek-v4-pro-02 成功 1212 200 113
DeepSeek-v4-pro-02 成功 1349 200 113
DeepSeek-v4-pro-02 成功 1128 200 113
jd-gemini-3.1-pro-preview 成功 3127 200 26
jd-gemini-3.1-pro-preview 成功 28161 200 26
腾讯 Gemini 3.5 Flash 成功 5077 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
jd-gemini-3.1-pro-preview 失败 30214 - - timeout: The read operation timed out
腾讯 Gemini 3.5 Flash 成功 4709 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 5162 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 3661 200 188 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 4718 200 264 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 558 403 - 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 539 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 464 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 514 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 3726 200 192 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 447 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 4519 200 115
Kimi K3 - Aliyun Bailian 成功 2724 200 115
Kimi K3 - Aliyun Bailian 成功 8102 200 115
Kimi K3 成功 6625 200 200 {"status":"ok","message":"stable"}
Kimi K3 成功 5661 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 4523 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 6282 200 140 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 6095 200 193 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 6383 200 183 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2303 200 138 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2462 200 128 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 219 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 154 400 - 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
Qwen3.8-Max 成功 2951 200 127 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5591 200 145 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 7901 200 152 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 5013 200 136 {"status":"ok","message":"stable"}