测试结果
Run ID: 20260828-131159-6eb01161
总请求45
成功 / 失败36/9
成功率80.0%
平均延迟3013 ms
P95 / Tokens6214 / 4345
| 渠道 | 模型 | 成功 | 失败 | 成功率 | 失败率 | 稳定性 | 平均延迟 ms | P95 ms | Tokens | 首个错误 |
|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek-v4-pro-04 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1149 | 1396 | 339 | |
| DeepSeek-v4-pro-01 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1200 | 1255 | 339 | |
| DeepSeek-v4-pro-03 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1203 | 1368 | 339 | |
| DeepSeek-v4-pro-02 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1355 | 1448 | 339 | |
| Kimi K3 - Aliyun Bailian | kimi/kimi-k3 | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1933 | 2316 | 345 | |
| Qwen3.8-Max | qwen3.8-max | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1992 | 2209 | 399 | |
| jd-gemini-3.1-pro-preview | gemini-3.1-pro-preview | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 2456 | 2626 | 78 | |
| Kimi K3 - TopenRouter | kimi-k3 | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 2670 | 4614 | 346 | |
| 腾讯 Gemini 3.5 Flash | gemini-3.5-flash | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 4281 | 4432 | 78 | |
| qwen3.6-plus | qwen3.6-plus | 3/3 | 0/3 | 100.0% | 0.0% | 可用 | 4686 | 6030 | 793 | |
| Kimi K3 | kimi-k3 | 3/3 | 0/3 | 100.0% | 0.0% | 可用 | 6276 | 8165 | 461 | |
| yulin-gemini-3.7-flash-high | gemini-3.7-flash-high | 3/3 | 0/3 | 100.0% | 0.0% | 可用 | 6954 | 10109 | 489 | |
| 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
无输出内容。
#2 DeepSeek-v4-pro-01
成功
HTTP 200
无输出内容。
#3 DeepSeek-v4-pro-01
成功
HTTP 200
无输出内容。
#4 DeepSeek-v4-pro-03
成功
HTTP 200
无输出内容。
#5 DeepSeek-v4-pro-03
成功
HTTP 200
无输出内容。
#6 DeepSeek-v4-pro-03
成功
HTTP 200
无输出内容。
#7 DeepSeek-v4-pro-04
成功
HTTP 200
无输出内容。
#8 DeepSeek-v4-pro-04
成功
HTTP 200
无输出内容。
#9 DeepSeek-v4-pro-04
成功
HTTP 200
无输出内容。
#10 DeepSeek-v4-pro-02
成功
HTTP 200
无输出内容。
#11 DeepSeek-v4-pro-02
成功
HTTP 200
无输出内容。
#12 DeepSeek-v4-pro-02
成功
HTTP 200
无输出内容。
#13 jd-gemini-3.1-pro-preview
成功
HTTP 200
无输出内容。
#14 jd-gemini-3.1-pro-preview
成功
HTTP 200
无输出内容。
#15 jd-gemini-3.1-pro-preview
成功
HTTP 200
无输出内容。
#16 腾讯 Gemini 3.5 Flash
成功
HTTP 200
{"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
{"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
{"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
```json
{"status":"ok","message":"stable"}
```
#20 qwen3.6-plus
成功
HTTP 200
{"status":"ok","message":"stable"}
#21 pixflow-gemini-3.1-pro-preview
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#22 pixflow-gemini-3.1-pro-preview
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#23 pixflow-gemini-3.1-pro-preview
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#24 yuling-gpt-5.5
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#25 qwen3.6-plus
成功
HTTP 200
{"status":"ok","message":"stable"}
#26 yuling-gpt-5.5
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#27 yuling-gpt-5.5
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#28 Kimi K3 - Aliyun Bailian
成功
HTTP 200
无输出内容。
#29 Kimi K3 - Aliyun Bailian
成功
HTTP 200
无输出内容。
#30 Kimi K3 - Aliyun Bailian
成功
HTTP 200
无输出内容。
#31 Kimi K3
成功
HTTP 200
{"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only JSON: {\"status"}, "logprobs": null, "finish_reason": "length"}
#32 Kimi K3
成功
HTTP 200
{"status":"ok","message":"stable"}
#33 Kimi K3
成功
HTTP 200
{"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"}
#34 Kimi K3 - TopenRouter
成功
HTTP 200
无输出内容。
#35 Kimi K3 - TopenRouter
成功
HTTP 200
无输出内容。
#36 Qwen3.8-Max
成功
HTTP 200
{"status":"ok","message":"stable"}
#37 Qwen3.8-Max
成功
HTTP 200
{"status":"ok","message":"stable"}
#38 Kimi K3 - TopenRouter
成功
HTTP 200
无输出内容。
#39 MiniMax H3 Context IR
失败
HTTP 400
HTTP 400: binding: expr_path=content, cause=missing required parameter
#40 MiniMax H3 Context IR
失败
HTTP 400
HTTP 400: binding: expr_path=content, cause=missing required parameter
#41 MiniMax H3 Context IR
失败
HTTP 400
HTTP 400: binding: expr_path=content, cause=missing required parameter
#42 Qwen3.8-Max
成功
HTTP 200
{"status":"ok","message":"stable"}
#43 yulin-gemini-3.7-flash-high
成功
HTTP 200
{"status":"ok","message":"stable"}
#44 yulin-gemini-3.7-flash-high
成功
HTTP 200
{"status":"ok","message":"stable"}
#45 yulin-gemini-3.7-flash-high
成功
HTTP 200
{"status":"ok","message":"stable"}
表格明细
| 渠道 | 状态 | 延迟 ms | HTTP | Tokens | 输出 / 错误 |
|---|---|---|---|---|---|
| DeepSeek-v4-pro-01 | 成功 | 1138 | 200 | 113 | |
| DeepSeek-v4-pro-01 | 成功 | 1255 | 200 | 113 | |
| DeepSeek-v4-pro-01 | 成功 | 1209 | 200 | 113 | |
| DeepSeek-v4-pro-03 | 成功 | 1155 | 200 | 113 | |
| DeepSeek-v4-pro-03 | 成功 | 1088 | 200 | 113 | |
| DeepSeek-v4-pro-03 | 成功 | 1368 | 200 | 113 | |
| DeepSeek-v4-pro-04 | 成功 | 940 | 200 | 113 | |
| DeepSeek-v4-pro-04 | 成功 | 1396 | 200 | 113 | |
| DeepSeek-v4-pro-04 | 成功 | 1112 | 200 | 113 | |
| DeepSeek-v4-pro-02 | 成功 | 1448 | 200 | 113 | |
| DeepSeek-v4-pro-02 | 成功 | 1296 | 200 | 113 | |
| DeepSeek-v4-pro-02 | 成功 | 1323 | 200 | 113 | |
| jd-gemini-3.1-pro-preview | 成功 | 2407 | 200 | 26 | |
| jd-gemini-3.1-pro-preview | 成功 | 2335 | 200 | 26 | |
| jd-gemini-3.1-pro-preview | 成功 | 2626 | 200 | 26 | |
| 腾讯 Gemini 3.5 Flash | 成功 | 4194 | 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 | 4432 | 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 | 4217 | 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 | 3616 | 200 | 206 | ```json {"status":"ok","message":"stable"} ``` |
| qwen3.6-plus | 成功 | 4412 | 200 | 240 | {"status":"ok","message":"stable"} |
| pixflow-gemini-3.1-pro-preview | 失败 | 505 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| pixflow-gemini-3.1-pro-preview | 失败 | 836 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| pixflow-gemini-3.1-pro-preview | 失败 | 503 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| yuling-gpt-5.5 | 失败 | 480 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| qwen3.6-plus | 成功 | 6030 | 200 | 347 | {"status":"ok","message":"stable"} |
| yuling-gpt-5.5 | 失败 | 530 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| yuling-gpt-5.5 | 失败 | 484 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| Kimi K3 - Aliyun Bailian | 成功 | 1380 | 200 | 115 | |
| Kimi K3 - Aliyun Bailian | 成功 | 2104 | 200 | 115 | |
| Kimi K3 - Aliyun Bailian | 成功 | 2316 | 200 | 115 | |
| Kimi K3 | 成功 | 5987 | 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 | 8165 | 200 | 231 | {"status":"ok","message":"stable"} |
| Kimi K3 | 成功 | 4676 | 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 - TopenRouter | 成功 | 1441 | 200 | 115 | |
| Kimi K3 - TopenRouter | 成功 | 1955 | 200 | 115 | |
| Qwen3.8-Max | 成功 | 1872 | 200 | 130 | {"status":"ok","message":"stable"} |
| Qwen3.8-Max | 成功 | 1895 | 200 | 129 | {"status":"ok","message":"stable"} |
| Kimi K3 - TopenRouter | 成功 | 4614 | 200 | 116 | |
| MiniMax H3 Context IR | 失败 | 257 | 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 | 186 | 400 | - | HTTP 400: binding: expr_path=content, cause=missing required parameter |
| Qwen3.8-Max | 成功 | 2209 | 200 | 140 | {"status":"ok","message":"stable"} |
| yulin-gemini-3.7-flash-high | 成功 | 6214 | 200 | 175 | {"status":"ok","message":"stable"} |
| yulin-gemini-3.7-flash-high | 成功 | 4539 | 200 | 170 | {"status":"ok","message":"stable"} |
| yulin-gemini-3.7-flash-high | 成功 | 10109 | 200 | 144 | {"status":"ok","message":"stable"} |