Logistics Intent Classification (17 Leaf Intents, Hierarchical): leaderboard
Metric: Accuracy (micro-F1, %) of predicting the query's leaf intent among 17 with hierarchical decoding (parent intent first, then its children) on the seen-language test split (native English, Spanish and Arabic user queries from a logistics platform's customer-service logs, de-identified, human-verified labels, natural traffic distribution), the model prompted with intent definitions and few-shot demonstrations; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 1.8 | 91.23 | #136 |
| 2 | DeepSeek V3.2 | 89.85 | #198 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=logistics-intent-classification-17-leaf-intents-hierarchical · How It Works · Data refreshed daily, snapshot 2026-10-11.