Contact us
Updated 2026-06-26

Which AI is best
for Scandinavian?

We evaluate over 350 AI models every morning and present the best. Google: Gemma 3 4B currently leads with 8.5/10.

See benchmark Compare models

What do you need to do?

Best choice
Meta: Llama 3.2 3B Instruct
meta-llama
$0.05/1M tokens
Cheapest option
Meta: Llama 3.2 3B Instruct
meta-llama
$0.05/1M tokens
Free alternative
Nearest free alternative
Perplexity: Sonar Pro Search
Free (with limits)

Which AI are you using today?

AI orchestrator: Different models excel at different tasks. Use our results to choose the right model for writing, coding, research and API cost. See orchestrator ranking →

Today's ranking

See full benchmark →
Tested 2026-06-26
# Model Tier t/s Nordic Instr Score Price/1M
1
Google: Gemma 3 4B
google
Stable
Budget 221 8.0 10.0 8.5 $0.05
≈0 kr
2
Meta: Llama 3.2 3B Instruct
meta-llama
Stable
Budget 260 8.0 8.0 7.9 $0.05
≈0 kr
3
Meta: Llama 4 Scout
meta-llama
 Mid-range 157 6.0 10.0 7.4 $0.10
≈1 kr
4
Qwen: Qwen3.5-Flash
qwen
 Budget 4125 4.0 10.0 7.4 $0.07
≈1 kr
5
Perplexity: Sonar Pro Search
perplexity
Stable
Premium 55 8.0 10.0 7.2 $3.00
≈30 kr
6
OpenAI: GPT-5.4 Nano
openai
Stable
Mid-range 155 6.0 10.0 7.2 $0.20
≈2 kr
7
Cohere: Command R+ (08-2024)
cohere
Stable
Premium 150 6.0 10.0 6.9 $2.50
≈25 kr
8
Cohere: Command R7B (12-2024)
cohere
Stable
Budget 190 6.0 8.0 6.8 $0.04
≈0 kr
9
Anthropic: Claude Haiku 4.5
anthropic
 Mid-range 116 6.0 10.0 6.7 $1.00
≈10 kr
10
Anthropic: Claude Sonnet 4.6
anthropic
Stable
Premium 104 6.0 10.0 6.6 $3.00
≈30 kr
11
OpenAI: GPT-5.5 Pro
openai
 Premium 321 4.0 8.0 6.5 $30.00
≈296 kr
12
Google: Gemini 2.5 Pro
google
Stable
Mid-range 150 8.0 2.0 4.5 $1.25
≈12 kr
Trend over last 7 days Full history →
20.621.622.623.624.625.626.6
Gemma 3 4B Llama 3.2 3B Instruct Llama 4 Scout Qwen3.5-Flash Sonar Pro Search

The chart shows direction — exact figures are for paying customers only

Latest events

🆕
26. JunNew model: OpenAI: GPT-5.5 Pro debuts with score 6.5
🆕
26. JunNew model: Meta: Llama 4 Scout debuts with score 7.4
🆕
26. JunNew model: Qwen: Qwen3.5-Flash debuts with score 7.4
↓
26. JunCommand R+ dropped from 8.4 to 6.9
↓
26. JunGemini 2.5 Pro dropped from 5.5 to 4.5
See all models we compare →