历史详情

Run ID: 20260829-053204-2c6a35ac

返回历史

测试结果

Run ID: 20260829-053204-2c6a35ac

导出 JSON
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟2953 ms
P95 / Tokens6998 / 4417
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-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1049 1338 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1106 1157 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1265 1391 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1348 1532 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2100 2246 400
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2241 3212 345
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2397 2878 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 稳定 2555 2743 494
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2907 3244 345
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 稳定 4375 4597 78
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5943 6998 345
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 8153 9585 976
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：1322 ms Tokens：113 时间：2026-08-29 05:31:08
JSON
{"status
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1532 ms Tokens：113 时间：2026-08-29 05:31:08
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1190 ms Tokens：113 时间：2026-08-29 05:31:10
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1136 ms Tokens：113 时间：2026-08-29 05:31:10
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1157 ms Tokens：113 时间：2026-08-29 05:31:11
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1025 ms Tokens：113 时间：2026-08-29 05:31:11
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型：deepseek-v4-pro 延迟：632 ms Tokens：113 时间：2026-08-29 05:31:12
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1178 ms Tokens：113 时间：2026-08-29 05:31:12
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1338 ms Tokens：113 时间：2026-08-29 05:31:13
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1137 ms Tokens：113 时间：2026-08-29 05:31:13
JSON
{"status":"ok","message
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1391 ms Tokens：113 时间：2026-08-29 05:31:14
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1269 ms Tokens：113 时间：2026-08-29 05:31:14
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：2112 ms Tokens：26 时间：2026-08-29 05:31:16
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：2878 ms Tokens：26 时间：2026-08-29 05:31:15
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：2203 ms Tokens：26 时间：2026-08-29 05:31:18
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：4195 ms Tokens：26 时间：2026-08-29 05:31:18
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：4597 ms Tokens：26 时间：2026-08-29 05:31:20
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：4335 ms Tokens：26 时间：2026-08-29 05:31:23
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：6194 ms Tokens：231 时间：2026-08-29 05:31:27
JSON
{"status":"ok","message":"stable"}
#20 qwen3.6-plus 成功 HTTP 200
模型：qwen3.6-plus 延迟：9585 ms Tokens：399 时间：2026-08-29 05:31:25
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：530 ms Tokens：- 时间：2026-08-29 05:31:34
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：525 ms Tokens：- 时间：2026-08-29 05:31:35
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：487 ms Tokens：- 时间：2026-08-29 05:31:35
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：461 ms Tokens：- 时间：2026-08-29 05:31:36
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：473 ms Tokens：- 时间：2026-08-29 05:31:36
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：483 ms Tokens：- 时间：2026-08-29 05:31:37
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型：kimi/kimi-k3 延迟：2344 ms Tokens：115 时间：2026-08-29 05:31:37
JSON
无输出内容。
#28 qwen3.6-plus 成功 HTTP 200
模型：qwen3.6-plus 延迟：8680 ms Tokens：346 时间：2026-08-29 05:31:33
JSON
{"status":"ok","message":"stable"}
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型：kimi/kimi-k3 延迟：3244 ms Tokens：115 时间：2026-08-29 05:31:39
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型：kimi/kimi-k3 延迟：3133 ms Tokens：115 时间：2026-08-29 05:31:42
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型：kimi-k3 延迟：5925 ms Tokens：115 时间：2026-08-29 05:31:43
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to only reply with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#32 Kimi K3 成功 HTTP 200
模型：kimi-k3 延迟：6998 ms Tokens：115 时间：2026-08-29 05:31:45
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#33 Kimi K3 成功 HTTP 200
模型：kimi-k3 延迟：4907 ms Tokens：115 时间：2026-08-29 05:31:49
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"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型：kimi-k3 延迟：1371 ms Tokens：115 时间：2026-08-29 05:31:54
JSON
{"status":"ok
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型：kimi-k3 延迟：3212 ms Tokens：115 时间：2026-08-29 05:31:52
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型：qwen3.8-max 延迟：1876 ms Tokens：134 时间：2026-08-29 05:31:55
JSON
{"status":"ok","message":"stable"}
#37 Kimi K3 - TopenRouter 成功 HTTP 200
模型：kimi-k3 延迟：2141 ms Tokens：115 时间：2026-08-29 05:31:55
JSON
{"status":"ok","message":"
#38 Qwen3.8-Max 成功 HTTP 200
模型：qwen3.8-max 延迟：2246 ms Tokens：140 时间：2026-08-29 05:31:57
JSON
{"status":"ok","message":"stable"}
#39 Qwen3.8-Max 成功 HTTP 200
模型：qwen3.8-max 延迟：2178 ms Tokens：126 时间：2026-08-29 05:31:57
JSON
{"status":"ok","message":"stable"}
#40 MiniMax H3 Context IR 失败 HTTP 400
模型：MiniMax-H3 延迟：197 ms Tokens：- 时间：2026-08-29 05:31:59
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：198 ms Tokens：- 时间：2026-08-29 05:31:59
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：215 ms Tokens：- 时间：2026-08-29 05:31:59
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：2743 ms Tokens：190 时间：2026-08-29 05:31:59
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：2641 ms Tokens：135 时间：2026-08-29 05:32:00
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：2282 ms Tokens：169 时间：2026-08-29 05:32:02
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 1322 200 113 {"status
DeepSeek-v4-pro-01 成功 1532 200 113
DeepSeek-v4-pro-01 成功 1190 200 113
DeepSeek-v4-pro-03 成功 1136 200 113
DeepSeek-v4-pro-03 成功 1157 200 113
DeepSeek-v4-pro-03 成功 1025 200 113
DeepSeek-v4-pro-04 成功 632 200 113
DeepSeek-v4-pro-04 成功 1178 200 113
DeepSeek-v4-pro-04 成功 1338 200 113
DeepSeek-v4-pro-02 成功 1137 200 113 {"status":"ok","message
DeepSeek-v4-pro-02 成功 1391 200 113
DeepSeek-v4-pro-02 成功 1269 200 113
jd-gemini-3.1-pro-preview 成功 2112 200 26
jd-gemini-3.1-pro-preview 成功 2878 200 26
jd-gemini-3.1-pro-preview 成功 2203 200 26
腾讯 Gemini 3.5 Flash 成功 4195 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 4597 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 4335 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 6194 200 231 {"status":"ok","message":"stable"}
qwen3.6-plus 成功 9585 200 399 {"status":"ok","message":"stable"}
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 525 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 487 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 461 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 473 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 483 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 2344 200 115
qwen3.6-plus 成功 8680 200 346 {"status":"ok","message":"stable"}
Kimi K3 - Aliyun Bailian 成功 3244 200 115
Kimi K3 - Aliyun Bailian 成功 3133 200 115
Kimi K3 成功 5925 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to only reply with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 6998 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply only with JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 4907 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 - TopenRouter 成功 1371 200 115 {"status":"ok
Kimi K3 - TopenRouter 成功 3212 200 115
Qwen3.8-Max 成功 1876 200 134 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2141 200 115 {"status":"ok","message":"
Qwen3.8-Max 成功 2246 200 140 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2178 200 126 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 197 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 198 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 215 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 2743 200 190 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2641 200 135 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 2282 200 169 {"status":"ok","message":"stable"}