Kinship Term Generation: leaderboard

Metric: Accepted-term accuracy (%; birthday greetings and wedding invitations, 462 responses per model; fully specified relationship (L3) prompts for 25 kinship relations in Hindi, Tamil and Korean, three runs per prompt at temperature 0.7; a response counts as correct when an accepted native-script kinship term (with listed spelling and honorific variants) appears in it). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.

Top models

#ModelScore
1GLM-5.172.29
2Kimi K2.648.7
3GPT-OSS-120B35.06
4Llama 3.3 70B Instruct24.24

Interactive version: theaggregate.ai/benchmark?slug=kinship-term-generation · How It Works · Data refreshed daily, snapshot 2026-09-26.