LexNeo-Bench (KG-Graph Context): leaderboard

Metric: Accuracy (%; borrowing-type classification of a highlighted token in a Luxembourgish RTL news sentence among native, French loan and German loan (English loan offered as a distractor label); 1,000 items per class; outputs that cannot be mapped to a label are dropped; temperature 0; an instance-specific subgraph of the authors' linguistic knowledge graph (donor chains from the Luxembourgish Online Dictionary, analogues, contrastive patterns) prepended to the prompt). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.

Top models

#ModelScore
1Gemma 3 12B (IT)81
2Gemma 3 27B (IT)71.4
3Llama 3.3 70B Instruct71.3

Interactive version: theaggregate.ai/benchmark?slug=lexneo-bench-kg-graph-context · How It Works · Data refreshed daily, snapshot 2026-09-26.