测试结果
Run ID: 20260829-144042-bf0e9d6b
总请求45
成功 / 失败35/10
成功率77.78%
平均延迟2781 ms
P95 / Tokens5144 / 4598
| 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 | 1143 | 1228 | 339 | |
| DeepSeek-v4-pro-02 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1173 | 1248 | 339 | |
| DeepSeek-v4-pro-03 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1372 | 1531 | 339 | |
| DeepSeek-v4-pro-01 | deepseek-v4-pro | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1574 | 1620 | 339 | |
| Kimi K3 - TopenRouter | kimi-k3 | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 1658 | 2490 | 345 | |
| Qwen3.8-Max | qwen3.8-max | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 2100 | 2531 | 386 | |
| Kimi K3 - Aliyun Bailian | kimi/kimi-k3 | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 2817 | 3173 | 345 | |
| yulin-gemini-3.7-flash-high | gemini-3.7-flash-high | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 3542 | 4940 | 508 | |
| 腾讯 Gemini 3.5 Flash | gemini-3.5-flash | 3/3 | 0/3 | 100.0% | 0.0% | 稳定 | 4483 | 4506 | 78 | |
| Kimi K3 | kimi-k3 | 3/3 | 0/3 | 100.0% | 0.0% | 可用 | 5166 | 6248 | 436 | |
| qwen3.6-plus | qwen3.6-plus | 3/3 | 0/3 | 100.0% | 0.0% | 可用 | 5180 | 8037 | 854 | |
| jd-gemini-3.1-pro-preview | gemini-3.1-pro-preview | 2/3 | 1/3 | 66.67% | 33.33% | 不稳定 | 3360 | 4284 | 290 | 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
无输出内容。
#2 DeepSeek-v4-pro-01
成功
HTTP 200
无输出内容。
#3 DeepSeek-v4-pro-03
成功
HTTP 200
无输出内容。
#4 DeepSeek-v4-pro-01
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
{"status":"ok","message":"stable"}
#15 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
#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 qwen3.6-plus
成功
HTTP 200
{"status":"ok","message":"stable"}
#19 jd-gemini-3.1-pro-preview
失败
HTTP -
timeout: The read operation timed out
#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 qwen3.6-plus
成功
HTTP 200
{"status":"ok","message":"stable"}
#25 yuling-gpt-5.5
失败
HTTP 403
HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}
#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 a JSON: {\""}, "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 Kimi K3 - TopenRouter
成功
HTTP 200
{"status":"ok","message
#37 Qwen3.8-Max
成功
HTTP 200
{"status":"ok","message":"stable"}
#38 Qwen3.8-Max
成功
HTTP 200
{"status":"ok","message":"stable"}
#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 | 1529 | 200 | 113 | |
| DeepSeek-v4-pro-01 | 成功 | 1574 | 200 | 113 | |
| DeepSeek-v4-pro-03 | 成功 | 1531 | 200 | 113 | |
| DeepSeek-v4-pro-01 | 成功 | 1620 | 200 | 113 | |
| DeepSeek-v4-pro-03 | 成功 | 1184 | 200 | 113 | |
| DeepSeek-v4-pro-03 | 成功 | 1403 | 200 | 113 | |
| DeepSeek-v4-pro-04 | 成功 | 1228 | 200 | 113 | |
| DeepSeek-v4-pro-04 | 成功 | 1202 | 200 | 113 | |
| DeepSeek-v4-pro-04 | 成功 | 1001 | 200 | 113 | |
| DeepSeek-v4-pro-02 | 成功 | 1248 | 200 | 113 | |
| DeepSeek-v4-pro-02 | 成功 | 1198 | 200 | 113 | |
| DeepSeek-v4-pro-02 | 成功 | 1073 | 200 | 113 | |
| jd-gemini-3.1-pro-preview | 成功 | 2437 | 200 | 26 | |
| jd-gemini-3.1-pro-preview | 成功 | 4284 | 200 | 264 | {"status":"ok","message":"stable"} |
| 腾讯 Gemini 3.5 Flash | 成功 | 4506 | 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 | 4489 | 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 | 4455 | 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 | 8037 | 200 | 466 | {"status":"ok","message":"stable"} |
| jd-gemini-3.1-pro-preview | 失败 | 30255 | - | - | timeout: The read operation timed out |
| qwen3.6-plus | 成功 | 3595 | 200 | 187 | {"status":"ok","message":"stable"} |
| pixflow-gemini-3.1-pro-preview | 失败 | 529 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| pixflow-gemini-3.1-pro-preview | 失败 | 576 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| pixflow-gemini-3.1-pro-preview | 失败 | 477 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| qwen3.6-plus | 成功 | 3908 | 200 | 201 | {"status":"ok","message":"stable"} |
| yuling-gpt-5.5 | 失败 | 526 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| yuling-gpt-5.5 | 失败 | 515 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| yuling-gpt-5.5 | 失败 | 703 | 403 | - | HTTP 403: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"} |
| Kimi K3 - Aliyun Bailian | 成功 | 2557 | 200 | 115 | |
| Kimi K3 - Aliyun Bailian | 成功 | 2723 | 200 | 115 | |
| Kimi K3 - Aliyun Bailian | 成功 | 3173 | 200 | 115 | |
| Kimi K3 | 成功 | 4106 | 200 | 115 | {"index": 0, "message": {"role": "assistant", "content": null, "reasoning": "The user is asking me to reply with only a JSON: {\""}, "logprobs": null, "finish_reason": "length"} |
| Kimi K3 | 成功 | 6248 | 200 | 206 | {"status":"ok","message":"stable"} |
| Kimi K3 | 成功 | 5144 | 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 | 1584 | 200 | 115 | |
| Kimi K3 - TopenRouter | 成功 | 2490 | 200 | 115 | |
| Kimi K3 - TopenRouter | 成功 | 900 | 200 | 115 | {"status":"ok","message |
| Qwen3.8-Max | 成功 | 1555 | 200 | 130 | {"status":"ok","message":"stable"} |
| Qwen3.8-Max | 成功 | 2531 | 200 | 119 | {"status":"ok","message":"stable"} |
| MiniMax H3 Context IR | 失败 | 198 | 400 | - | HTTP 400: binding: expr_path=content, cause=missing required parameter |
| MiniMax H3 Context IR | 失败 | 174 | 400 | - | HTTP 400: binding: expr_path=content, cause=missing required parameter |
| MiniMax H3 Context IR | 失败 | 179 | 400 | - | HTTP 400: binding: expr_path=content, cause=missing required parameter |
| Qwen3.8-Max | 成功 | 2214 | 200 | 137 | {"status":"ok","message":"stable"} |
| yulin-gemini-3.7-flash-high | 成功 | 2949 | 200 | 199 | {"status":"ok","message":"stable"} |
| yulin-gemini-3.7-flash-high | 成功 | 4940 | 200 | 160 | {"status":"ok","message":"stable"} |
| yulin-gemini-3.7-flash-high | 成功 | 2738 | 200 | 149 | {"status":"ok","message":"stable"} |