NorwAI-Mistral-7B: benchmark results

Provider: NorwAI. Released 2024-05-15. Access: Open.

Aggregate Rating 1261 ± 42, rank #9157 of 10916 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Dutch NLU - DBRD85.17Matthews correlation coefficient (%)43.7
EuroEval Danish Knowledge37.8Knowledge Average Score (%)41
EuroEval Danish Knowledge - Danish Citizen Tests37.8MCC (x100)36.4
EuroEval Portuguese NLU - SST-2 PT69.87Matthews correlation coefficient (%)35.9
EuroEval Portuguese NLU - MultiWikiQA PT61.21Character F1 (%)34.6
EuroEval Norwegian Knowledge5.22Knowledge Average Score (%)29.4
EuroEval Norwegian Knowledge - NRK Quiz QA10.05MCC (x100)28.5
EuroEval Portuguese NLU36.93NLU Average Score (%)26.8
EuroEval Norwegian Knowledge - Idioms NO0.38MCC (x100)26.5
EuroEval Portuguese Common Sense Reasoning1.34Common Sense Reasoning Average Score (%)20.2
EuroEval Portuguese24.86Average Score (%)19.8
EuroEval Norwegian Common Sense Reasoning2.11Common Sense Reasoning Average Score (%)18.5

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