历史详情

Run ID: 20260827-225113-27f2fa7a

返回历史

测试结果

Run ID: 20260827-225113-27f2fa7a

导出 JSON
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟3948 ms
P95 / Tokens7689 / 4008
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 1115 1165 339
DeepSeek-v4-pro-04 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1219 1336 339
DeepSeek-v4-pro-02 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1253 1452 339
DeepSeek-v4-pro-03 deepseek-v4-pro 3/3 0/3 100.0% 0.0% 稳定 1285 1651 339
Qwen3.8-Max qwen3.8-max 3/3 0/3 100.0% 0.0% 稳定 2175 2360 387
jd-gemini-3.1-pro-preview gemini-3.1-pro-preview 3/3 0/3 100.0% 0.0% 稳定 2571 2636 78
qwen3.6-plus qwen3.6-plus 3/3 0/3 100.0% 0.0% 可用 4539 5545 741
Kimi K3 kimi-k3 3/3 0/3 100.0% 0.0% 可用 4840 5203 345
腾讯 Gemini 3.5 Flash gemini-3.5-flash 3/3 0/3 100.0% 0.0% 可用 5521 5596 78
yulin-gemini-3.7-flash-high gemini-3.7-flash-high 3/3 0/3 100.0% 0.0% 可用 7590 7860 433
Kimi K3 - TopenRouter kimi-k3 3/3 0/3 100.0% 0.0% 可用 8877 21039 360
Kimi K3 - Aliyun Bailian kimi/kimi-k3 2/3 1/3 66.67% 33.33% 不稳定 7618 7643 230 HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"7a6a3cb9-270c-90a6-beb7-96111b601202"}
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：1079 ms Tokens：113 时间：2026-08-27 22:49:58
JSON
无输出内容。
#2 DeepSeek-v4-pro-01 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1102 ms Tokens：113 时间：2026-08-27 22:49:58
JSON
无输出内容。
#3 DeepSeek-v4-pro-03 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1075 ms Tokens：113 时间：2026-08-27 22:49:59
JSON
无输出内容。
#4 DeepSeek-v4-pro-01 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1165 ms Tokens：113 时间：2026-08-27 22:49:59
JSON
无输出内容。
#5 DeepSeek-v4-pro-03 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1129 ms Tokens：113 时间：2026-08-27 22:50:00
JSON
无输出内容。
#6 DeepSeek-v4-pro-03 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1651 ms Tokens：113 时间：2026-08-27 22:50:00
JSON
无输出内容。
#7 DeepSeek-v4-pro-04 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1128 ms Tokens：113 时间：2026-08-27 22:50:02
JSON
无输出内容。
#8 DeepSeek-v4-pro-04 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1336 ms Tokens：113 时间：2026-08-27 22:50:02
JSON
无输出内容。
#9 DeepSeek-v4-pro-04 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1195 ms Tokens：113 时间：2026-08-27 22:50:03
JSON
无输出内容。
#10 DeepSeek-v4-pro-02 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1452 ms Tokens：113 时间：2026-08-27 22:50:03
JSON
无输出内容。
#11 DeepSeek-v4-pro-02 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1093 ms Tokens：113 时间：2026-08-27 22:50:04
JSON
无输出内容。
#12 DeepSeek-v4-pro-02 成功 HTTP 200
模型：deepseek-v4-pro 延迟：1215 ms Tokens：113 时间：2026-08-27 22:50:05
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：2511 ms Tokens：26 时间：2026-08-27 22:50:05
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：2636 ms Tokens：26 时间：2026-08-27 22:50:06
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：2567 ms Tokens：26 时间：2026-08-27 22:50:07
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：5506 ms Tokens：26 时间：2026-08-27 22:50:09
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：5461 ms Tokens：26 时间：2026-08-27 22:50:10
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：3384 ms Tokens：172 时间：2026-08-27 22:50:15
JSON
{"status":"ok","message":"stable"}
#19 腾讯 Gemini 3.5 Flash 成功 HTTP 200
模型：gemini-3.5-flash 延迟：5596 ms Tokens：26 时间：2026-08-27 22:50:14
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
#20 qwen3.6-plus 成功 HTTP 200
模型：qwen3.6-plus 延迟：4688 ms Tokens：259 时间：2026-08-27 22:50:19
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：521 ms Tokens：- 时间：2026-08-27 22:50:24
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：520 ms Tokens：- 时间：2026-08-27 22:50:24
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：523 ms Tokens：- 时间：2026-08-27 22:50:25
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：5545 ms Tokens：310 时间：2026-08-27 22:50:20
JSON
{"status":"ok","message":"stable"}
#25 yuling-gpt-5.5 失败 HTTP 403
模型：gpt-5.5 延迟：551 ms Tokens：- 时间：2026-08-27 22:50:25
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：500 ms Tokens：- 时间：2026-08-27 22:50:25
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：450 ms Tokens：- 时间：2026-08-27 22:50:26
JSON
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#28 Kimi K3 - Aliyun Bailian 失败 HTTP 429
模型：kimi/kimi-k3 延迟：5750 ms Tokens：- 时间：2026-08-27 22:50:26
JSON
HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"7a6a3cb9-270c-90a6-beb7-96111b601202"}
#29 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型：kimi/kimi-k3 延迟：7643 ms Tokens：115 时间：2026-08-27 22:50:26
JSON
无输出内容。
#30 Kimi K3 成功 HTTP 200
模型：kimi-k3 延迟：5203 ms Tokens：115 时间：2026-08-27 22:50:34
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"}
#31 Kimi K3 - Aliyun Bailian 成功 HTTP 200
模型：kimi/kimi-k3 延迟：7594 ms Tokens：115 时间：2026-08-27 22:50:32
JSON
无输出内容。
#32 Kimi K3 成功 HTTP 200
模型：kimi-k3 延迟：4278 ms Tokens：115 时间：2026-08-27 22:50:39
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
#33 Kimi K3 成功 HTTP 200
模型：kimi-k3 延迟：5040 ms Tokens：115 时间：2026-08-27 22:50:39
JSON
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}
#34 Kimi K3 - TopenRouter 成功 HTTP 200
模型：kimi-k3 延迟：2698 ms Tokens：65 时间：2026-08-27 22:50:43
JSON
{"status":"ok","message":"stable"}
#35 Kimi K3 - TopenRouter 成功 HTTP 200
模型：kimi-k3 延迟：2894 ms Tokens：180 时间：2026-08-27 22:50:46
JSON
无输出内容。
#36 Qwen3.8-Max 成功 HTTP 200
模型：qwen3.8-max 延迟：2360 ms Tokens：130 时间：2026-08-27 22:50:49
JSON
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max 成功 HTTP 200
模型：qwen3.8-max 延迟：2022 ms Tokens：129 时间：2026-08-27 22:50:51
JSON
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max 成功 HTTP 200
模型：qwen3.8-max 延迟：2145 ms Tokens：128 时间：2026-08-27 22:50:53
JSON
{"status":"ok","message":"stable"}
#39 MiniMax H3 Context IR 失败 HTTP 400
模型：MiniMax-H3 延迟：172 ms Tokens：- 时间：2026-08-27 22:50:55
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：173 ms Tokens：- 时间：2026-08-27 22:50:55
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：2026-08-27 22:50:56
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：7221 ms Tokens：150 时间：2026-08-27 22:50:56
JSON
{"status":"ok","message":"stable"}
#43 Kimi K3 - TopenRouter 成功 HTTP 200
模型：kimi-k3 延迟：21039 ms Tokens：115 时间：2026-08-27 22:50:45
JSON
无输出内容。
#44 yulin-gemini-3.7-flash-high 成功 HTTP 200
模型：gemini-3.7-flash-high 延迟：7860 ms Tokens：143 时间：2026-08-27 22:51:03
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：7689 ms Tokens：140 时间：2026-08-27 22:51:06
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 1079 200 113
DeepSeek-v4-pro-01 成功 1102 200 113
DeepSeek-v4-pro-03 成功 1075 200 113
DeepSeek-v4-pro-01 成功 1165 200 113
DeepSeek-v4-pro-03 成功 1129 200 113
DeepSeek-v4-pro-03 成功 1651 200 113
DeepSeek-v4-pro-04 成功 1128 200 113
DeepSeek-v4-pro-04 成功 1336 200 113
DeepSeek-v4-pro-04 成功 1195 200 113
DeepSeek-v4-pro-02 成功 1452 200 113
DeepSeek-v4-pro-02 成功 1093 200 113
DeepSeek-v4-pro-02 成功 1215 200 113
jd-gemini-3.1-pro-preview 成功 2511 200 26
jd-gemini-3.1-pro-preview 成功 2636 200 26
jd-gemini-3.1-pro-preview 成功 2567 200 26
腾讯 Gemini 3.5 Flash 成功 5506 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 5461 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 3384 200 172 {"status":"ok","message":"stable"}
腾讯 Gemini 3.5 Flash 成功 5596 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 4688 200 259 {"status":"ok","message":"stable"}
pixflow-gemini-3.1-pro-preview 失败 521 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 520 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
pixflow-gemini-3.1-pro-preview 失败 523 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
qwen3.6-plus 成功 5545 200 310 {"status":"ok","message":"stable"}
yuling-gpt-5.5 失败 551 403 - HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
yuling-gpt-5.5 失败 500 403 - 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"}
Kimi K3 - Aliyun Bailian 失败 5750 429 - HTTP 429: {"error":{"message":"The engine is currently overloaded, please try again later","type":"EngineOverloadedError","param":null,"code":"EngineOverloadedError"},"request_id":"7a6a3cb9-270c-90a6-beb7-96111b601202"}
Kimi K3 - Aliyun Bailian 成功 7643 200 115
Kimi K3 成功 5203 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 - Aliyun Bailian 成功 7594 200 115
Kimi K3 成功 4278 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to respond with only JSON: {\"status\":\"ok\",\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 成功 5040 200 115 {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a specific JSON: {\"status\":\""}, "logprobs": null, "finish_reason": "length"}
Kimi K3 - TopenRouter 成功 2698 200 65 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 2894 200 180
Qwen3.8-Max 成功 2360 200 130 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2022 200 129 {"status":"ok","message":"stable"}
Qwen3.8-Max 成功 2145 200 128 {"status":"ok","message":"stable"}
MiniMax H3 Context IR 失败 172 400 - HTTP 400: binding: expr_path=content, cause=missing required parameter
MiniMax H3 Context IR 失败 173 400 - 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
yulin-gemini-3.7-flash-high 成功 7221 200 150 {"status":"ok","message":"stable"}
Kimi K3 - TopenRouter 成功 21039 200 115
yulin-gemini-3.7-flash-high 成功 7860 200 143 {"status":"ok","message":"stable"}
yulin-gemini-3.7-flash-high 成功 7689 200 140 {"status":"ok","message":"stable"}