Lamarck-14B-v0.7: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1554 ± 32, rank #1652 of 10916 rated models, from 55 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Portuguese LLM - ASSIN2 RTE94.2Macro F1 (%)95.2
Open Portuguese LLM - ENEM81.11Accuracy (%)94.8
Open Portuguese LLM - OAB Exams62.19Accuracy (%)94.7
Open Japanese LLM - Mbpp Pylint Check98.19Score (%)94.6
Open Portuguese LLM - BLUEX73.57Accuracy (%)94.6
Open Japanese LLM - CG62.85Score (%)92.3
Open Portuguese LLM - FaQuAD NLI79.89Macro F1 (%)88.6
Open Japanese LLM - Wiki Coreference SET F17.87Score (%)85.1
Open Japanese LLM Leaderboard64.98Average Score (%)81.7
Open Japanese LLM - Jemhopqa Char F158.88Score (%)78.1
Open Japanese LLM - Xlsum JA Bert Score JA F170.13Score (%)78
Open Japanese LLM - Jnli Exact Match86.07Score (%)76.3

Interactive version: theaggregate.ai/model?slug=lamarck-14b-v0-7 · How It Works · Data refreshed daily, snapshot 2026-11-08.