Independent Nordic AI benchmark

Which AI should you use today?

We evaluate over 350 AI models every morning and present the best choices for Nordic language quality, speed and value.

350+AI models tracked
2026-06-18Updated
Cohere: Command R+ (08-2024)Current top signal
8.7/10Score

Daily benchmark

See which models perform best right now for Nordic writing, instruction following, speed and price.

Choose by task

Use the results to choose models for writing, coding, research, API cost and everyday work.

No commercial ties

Recommendations are based on test results only. We do not have affiliate agreements with AI providers.

Updated model landscape

New models, silent provider updates and changing prices are reflected in the benchmark over time.

Nordic language focus

A strong English model is not always the best choice for Norwegian, Swedish or Danish work.

For individuals and teams

Use the public pages for quick choices, or the data products when you need repeatable model selection.

Today’s ranking

Independent. No affiliate agreements or commercial ties to AI providers.

Benchmark
#ModelTierNordicInstructiont/sScorePrice/1M
1Cohere: Command R+ (08-2024)coherePremium10.010.08.7
2Mistral Large 2407mistralaiMid-range8.010.08.5
3Mistral: Mistral Small 3mistralaiBudget6.010.08.2
4Meta: Llama 3.2 3B Instructmeta-llamaBudget8.08.08.1
5Anthropic: Claude Haiku 4.5anthropicMid-range8.010.07.7
6Google: Gemma 3 4BgoogleBudget6.010.07.6
7Anthropic: Claude Sonnet 4.6anthropicPremium8.010.07.5
8Cohere: Command R7B (12-2024)cohereBudget8.08.07.4

Explore more

Over 350 AI models are evaluated every day. The strongest results are presented for Nordic language work.