Large Language Model Evaluation on NorEval (test) benchmark leaderboard · SOTA2 Research

Large Language Model Evaluation on NorEval (test)

0.455Overall ScoreNorwAI-Mistral-7B

Evaluation Results

Method	Links
NorwAI-Mistral-7B2026.01		0.455	69	0.472	0.707	0.359	0.367	0.395	0.371	0.319	0.377	0.732
NorwAI-Llama2-7B2026.01		0.441	59	0.479	0.663	0.298	0.302	0.354	0.388	0.375	0.377	0.729
NorMistral-7B-warm2026.01		0.436	61	0.592	0.687	0.34	0.316	0.387	0.407	0.33	0.146	0.72
Viking 7B2026.01		0.419	47	0.513	0.595	0.274	0.266	0.25	0.259	0.494	0.387	0.73
NorMistral-7B-warm-IT2026.01		0.409	13	0.169	0.772	0.352	0.247	0.493	0.234	0.548	0.561	0.305
Mistral 7B2026.01		0.397	38	0.234	0.777	0.211	0.46	0.435	0.471	0.295	0.116	0.575
NorMistral-7B-scratch2026.01		0.385	32	0.532	0.575	0.277	0.403	0.254	0.223	0.359	0.149	0.697
NorBLOOM-7B-warm2026.01		0.356	28	0.518	0.408	0.235	0.391	0.233	0.239	0.356	0.139	0.688