munin-7B-core-pt-3: benchmark results

Provider: Other.

Aggregate Rating 1343 ± 39, rank #7889 of 10916 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Danish NLU - Multi Wiki QA DA69.63Character F1 (%)49.4
EuroEval Swedish NLU - Multi Wiki QA SV59.99Character F1 (%)39.1
EuroEval Danish NLU34.05NLU Average Score (%)35.8
EuroEval Danish28.13Average Score (%)34.7
EuroEval Danish Knowledge - Danske Talemaader22.37MCC (x100)34.5
EuroEval Danish Knowledge26.41Knowledge Average Score (%)33.6
EuroEval Danish Knowledge - Danish Citizen Tests30.44MCC (x100)32
EuroEval Danish NLU - Angry Tweets35.39Matthews correlation coefficient (%)31.7
EuroEval Danish Common Sense Reasoning7.88Common Sense Reasoning Average Score (%)26.4
EuroEval Danish NLU - Dansk31.19Micro F1 excluding MISC (%)21.3
EuroEval Danish NLU - ScaLA DA0Matthews correlation coefficient (%)9.7

Interactive version: theaggregate.ai/model?slug=munin-7b-core-pt-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.