emma-500-llama2-7B: benchmark results

Provider: MaLA-LM. Released 2024-05-01. Access: Open.

Aggregate Rating 1359 ± 38, rank #7468 of 10916 rated models, from 64 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval French NLU - FQuAD70.79Character F1 (%)79.9
EuroEval English NLU - SQuAD83.69Character F1 (%)77.9
EuroEval German NLU - Germanquad58.29Character F1 (%)76.9
EuroEval Swedish NLU - Swerec77.4Matthews correlation coefficient (%)75.5
EuroEval Norwegian NLU - Norquad68.63Character F1 (%)67.5
EuroEval Dutch NLU - SQuAD NL74.27Character F1 (%)61.1
EuroEval Icelandic NLU - NQII47.07Character F1 (%)53.8
EuroEval Portuguese NLU - MultiWikiQA PT69.42Character F1 (%)53.5
EuroEval Icelandic NLU - ScaLA IS5.45Matthews correlation coefficient (%)51.6
EuroEval French52.6Average Score (%)48.9
EuroEval Dutch50.87Average Score (%)46.8
EuroEval Portuguese NLU - SST-2 PT75.07Matthews correlation coefficient (%)45.6

Interactive version: theaggregate.ai/model?slug=emma-500-llama2-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.