Japanese Appointment Intent Classification
Can the agent classify short Japanese appointment messages into stable intent labels?
日本語客服wrong_intent
提示词摘要
Classify messages as booking, cancellation, reschedule, pricing_question, or other.
评分规则摘要
Must use only allowed labels and include short reasons.
任务排行榜
| Claude Main | 92 | 33% 严重失败 |
| Qwen Main | 81 | 33% 严重失败 |
| OpenAI Main | 79 | 33% 严重失败 |
| Gemini Main | 79 | 33% 严重失败 |
| DeepSeek Main | 79 | 0% 严重失败 |
| Grok Main | 73 | 33% 严重失败 |
常见失败标签
wrong_intentmissed_dependencytoo_verbosewrong_date_formatliteral_translationinvalid_json