munin-7B-core-pt: benchmark results

Provider: Other.

Aggregate Rating 1325 ± 40, rank #8254 of 10916 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Danish NLU - Multi Wiki QA DA65.95Character F1 (%)40.5
EuroEval Swedish NLU - Multi Wiki QA SV56.84Character F1 (%)37.5
EuroEval Danish NLU31.26NLU Average Score (%)32.1
EuroEval Danish NLU - Dansk38.78Micro F1 excluding MISC (%)29.9
EuroEval Danish24.32Average Score (%)29.3
EuroEval Danish Knowledge - Danske Talemaader14.73MCC (x100)29.3
EuroEval Danish Knowledge - Danish Citizen Tests25.66MCC (x100)29.1
EuroEval Danish Knowledge20.2Knowledge Average Score (%)28.7
EuroEval Danish Common Sense Reasoning4.82Common Sense Reasoning Average Score (%)23.3
EuroEval Danish NLU - Angry Tweets20.29Matthews correlation coefficient (%)19.3
EuroEval Danish NLU - ScaLA DA0Matthews correlation coefficient (%)9.7

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