历史详情

Run ID: 20260828-192017-c90d984e

返回历史

测试结果

Run ID: 20260828-192017-c90d984e

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟3846 ms
P95 / Tokens7480 / 4616
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 908 1171 339
DeepSeek-v4-pro-01 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1018 1095 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1144 1385 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1147 1860 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2297 2927 398
Kimi K3 - Aliyun Bailian kimi/kimi-k3 3/3 0/3 100.0% 0.0% 稳定 2867 3005 345
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 稳定 3627 3960 464
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 5425 6634 450
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 5874 7480 1016
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 6600 9032 78
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 12222 28566 457
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 2/3 1/3 66.67% 33.33% 不稳定 2620 2696 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:869 ms Tokens:113 时间:2026-08-28 19:18:52
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1090 ms Tokens:113 时间:2026-08-28 19:18:52
JSON
无输出内容。
#3 DeepSeek-v4-pro-01 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1095 ms Tokens:113 时间:2026-08-28 19:18:53
JSON
无输出内容。
#4 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:819 ms Tokens:113 时间:2026-08-28 19:18:54
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1860 ms Tokens:113 时间:2026-08-28 19:18:53
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型:deepseek-v4-pro 延迟:763 ms Tokens:113 时间:2026-08-28 19:18:55
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1171 ms Tokens:113 时间:2026-08-28 19:18:55
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:744 ms Tokens:113 时间:2026-08-28 19:18:56
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型:deepseek-v4-pro 延迟:810 ms Tokens:113 时间:2026-08-28 19:18:56
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1302 ms Tokens:113 时间:2026-08-28 19:18:56
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:1385 ms Tokens:113 时间:2026-08-28 19:18:57
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型:deepseek-v4-pro 延迟:745 ms Tokens:113 时间:2026-08-28 19:18:58
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:2696 ms Tokens:26 时间:2026-08-28 19:18:58
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:2544 ms Tokens:26 时间:2026-08-28 19:19:01
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:5405 ms Tokens:26 时间:2026-08-28 19:19:04
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 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:5365 ms Tokens:26 时间:2026-08-28 19:19:09
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
#17 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型:gemini-3.5-flash 延迟:9032 ms Tokens:26 时间:2026-08-28 19:19:14
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
#18 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5058 ms Tokens:291 时间:2026-08-28 19:19:24
JSON
{"status":"ok","message":"stable"}
#19 jd-gemini-3.1-pro-preview 失败 HTTP -
模型:gemini-3.1-pro-preview 延迟:30259 ms Tokens:- 时间:2026-08-28 19:18:58
JSON
timeout: The read operation timed out
#20 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:5086 ms Tokens:291 时间:2026-08-28 19:19:29
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:506 ms Tokens:- 时间:2026-08-28 19:19:34
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:512 ms Tokens:- 时间:2026-08-28 19:19:34
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:469 ms Tokens:- 时间:2026-08-28 19:19:35
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:536 ms Tokens:- 时间:2026-08-28 19:19:35
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#25 qwen3.6-plus 成功 HTTP 200
模型:qwen3.6-plus 延迟:7480 ms Tokens:434 时间:2026-08-28 19:19:29
JSON
{"status":"ok","message":"stable"}
#26 yuling-gpt-5.5 失败 HTTP 403
模型:gpt-5.5 延迟:546 ms Tokens:- 时间:2026-08-28 19:19:36
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:463 ms Tokens:- 时间:2026-08-28 19:19:36
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:3005 ms Tokens:115 时间:2026-08-28 19:19:36
JSON
无输出内容。
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2825 ms Tokens:115 时间:2026-08-28 19:19:37
JSON
无输出内容。
#30 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型:kimi/kimi-k3 延迟:2771 ms Tokens:115 时间:2026-08-28 19:19:39
JSON
无输出内容。
#31 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:5259 ms Tokens:115 时间:2026-08-28 19:19:39
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
#32 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:6634 ms Tokens:220 时间:2026-08-28 19:19:42
JSON
{"status":"ok","message":"stable"}
#33 Kimi K3 成功 HTTP 200
模型:kimi-k3 延迟:4382 ms Tokens:115 时间:2026-08-28 19:19:45
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:5051 ms Tokens:151 时间:2026-08-28 19:19:49
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:3050 ms Tokens:153 时间:2026-08-28 19:19:54
JSON
{"status":"ok","message":"stable"}
#36 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2017 ms Tokens:131 时间:2026-08-28 19:19:57
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:1949 ms Tokens:128 时间:2026-08-28 19:19:59
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型:qwen3.8-max 延迟:2927 ms Tokens:139 时间:2026-08-28 19:20:01
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型:MiniMax-H3 延迟:211 ms Tokens:- 时间:2026-08-28 19:20:04
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:214 ms Tokens:- 时间:2026-08-28 19:20:04
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:166 ms Tokens:- 时间:2026-08-28 19:20:05
JSON
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型:gemini-3.7-flash-high 延迟:3860 ms Tokens:145 时间:2026-08-28 19:20:05
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:3960 ms Tokens:147 时间:2026-08-28 19:20:09
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:3061 ms Tokens:172 时间:2026-08-28 19:20:13
JSON
{"status":"ok","message":"stable"}
#45 Kimi K3 - TopenRouter 成功 HTTP 200
模型:kimi-k3 延迟:28566 ms Tokens:153 时间:2026-08-28 19:19:49
JSON
无输出内容。

表格明细

渠道状态延迟 msHTTPTokens输出 / 错误
DeepSeek-v4-pro-01 成功 869 200 113
DeepSeek-v4-pro-01 成功 1090 200 113
DeepSeek-v4-pro-01 成功 1095 200 113
DeepSeek-v4-pro-03 成功 819 200 113
DeepSeek-v4-pro-03 成功 1860 200 113
DeepSeek-v4-pro-03 成功 763 200 113
DeepSeek-v4-pro-04 成功 1171 200 113
DeepSeek-v4-pro-04 成功 744 200 113
DeepSeek-v4-pro-04 成功 810 200 113
DeepSeek-v4-pro-02 成功 1302 200 113
DeepSeek-v4-pro-02 成功 1385 200 113
DeepSeek-v4-pro-02 成功 745 200 113
jd-gemini-3.1-pro-preview 成功 2696 200 26
jd-gemini-3.1-pro-preview 成功 2544 200 26
腾讯 Gemini 3.5 Flash 成功 5405 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 5365 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 9032 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 5058 200 291 {"status":"ok","message":"stable"}
jd-gemini-3.1-pro-preview 失败 30259 - - timeout: The read operation timed out
qwen3.6-plus 成功 5086 200 291 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 506 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 512 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 469 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 536 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 7480 200 434 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 546 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 463 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
Kimi K3 - Aliyun Bailian 成功 3005 200 115
Kimi K3 - Aliyun Bailian 成功 2825 200 115
Kimi K3 - Aliyun Bailian 成功 2771 200 115
Kimi K3 成功 5259 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 6634 200 220 {"status":"ok","message":"stable"}
Kimi K3 成功 4382 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only a specific JSON:"}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 5051 200 151 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 3050 200 153 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2017 200 131 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 1949 200 128 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2927 200 139 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 211 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 214 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 166 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
yulin-gemini-3.7-flash-high 成功 3860 200 145 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3960 200 147 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 3061 200 172 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 28566 200 153