Lamarck-14B-v0.6: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1572 ± 32, rank #1374 of 10916 rated models, from 61 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - GPQA38.93Score97.3
Open LLM Leaderboard - MMLU-Pro54Score96.2
Open LLM Leaderboard - MuSR48.47Score95.9
Open Portuguese LLM - ASSIN2 RTE94.28Macro F1 (%)95.6
Open Portuguese LLM - BLUEX73.57Accuracy (%)94.6
Open Portuguese LLM - OAB Exams61.64Accuracy (%)94.1
Open Portuguese LLM - ENEM80.34Accuracy (%)93.6
Open Japanese LLM - CG63.25Score (%)93.4
Open LLM Leaderboard - MATH Level 540.41Score90.3
Open LLM Leaderboard - BBH64.6Score90.1
Open Japanese LLM - Mbpp Pylint Check96.39Score (%)89.1
Open Portuguese LLM - FaQuAD NLI80Macro F1 (%)89.1

Interactive version: theaggregate.ai/model?slug=lamarck-14b-v0-6 · How It Works · Data refreshed daily, snapshot 2026-11-08.