Contact us
Updated 2026-06-28

Which AI should
you use?

Take a quick test and get an AI recommendation for your task. HvilkenAI evaluates over 350 AI models every morning — Google: Gemma 3 4B currently leads with 8.7/10.

Start the AI test See the data basis
Over 350 models evaluated Independent — no affiliate deals Updated daily

Free AI test

Choose a task. Get a recommended AI.

Like a quick test for AI: choose what you need to do, and we show the best choice, a lower-cost alternative and a free option where available.

1. Choose task 2. See recommendation 3. Check benchmark
0 kr

New full AI test

Answer four quick questions and get a more personal recommendation with free options first.

Open full test
Best choice
Google: Gemma 3 4B
google
$0.05/1M tokens
Cheapest option
Meta: Llama 3.2 3B Instruct
meta-llama
$0.05/1M tokens
Free alternative
Nearest free alternative
Cohere: Command R+ (08-2024)
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 →

The data behind the test

Today's ranking

The AI test uses the benchmark as its trust layer. Results combine standardised tasks, price, speed, stability and language understanding — presented as a simple recommendation.

See full benchmark →
Tested 2026-06-28
# Model Tier t/s Nordic Instr Score Price/1M
1
Google: Gemma 3 4B
google
Stable
Budget 245 8.0 10.0 8.7 $0.05
≈0 kr
2
Cohere: Command R+ (08-2024)
cohere
Stable
Premium 156 8.0 10.0 8.2 $2.50
≈25 kr
3
OpenAI: GPT-5.3-Codex
openai
 Mid-range 274 6.0 10.0 8.1 $1.75
≈17 kr
4
Anthropic: Claude Haiku 4.5
anthropic
Stable
Mid-range 119 8.0 10.0 7.7 $1.00
≈10 kr
5
Mistral Large 2407
mistralai
Stable
Mid-range 234 6.0 10.0 7.7 $2.00
≈20 kr
6
Cohere: Command R7B (12-2024)
cohere
Stable
Budget 184 8.0 8.0 7.6 $0.04
≈0 kr
7
Anthropic: Claude Sonnet 4.6
anthropic
Stable
Premium 90 8.0 10.0 7.4 $3.00
≈30 kr
8
Meta: Llama 3.2 3B Instruct
meta-llama
Stable
Budget 302 6.0 8.0 7.4 $0.05
≈0 kr
9
OpenAI: GPT-4 Turbo
openai
 Premium 92 6.0 10.0 6.7 $10.00
≈99 kr
10
Perplexity: Sonar Pro Search
perplexity
Stable
Premium 69 6.0 10.0 6.4 $3.00
≈30 kr
11
inclusionAI: Ling-2.6-flash
inclusionai
 Budget 127 4.0 10.0 6.4 $0.01
≈0 kr
12
Google: Gemini 2.5 Pro
google
Stable
Mid-range 124 8.0 4.0 5.5 $1.25
≈12 kr
Trend over last 7 days Full history →
22.623.624.625.626.627.628.6
Gemma 3 4B Command R+ GPT-5.3-Codex Claude Haiku 4.5 Mistral Large 2407

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

Latest events

🆕
28. JunNew model: OpenAI: GPT-4 Turbo debuts with score 6.7
🆕
28. JunNew model: Mistral Large 2407 debuts with score 7.7
🆕
28. JunNew model: OpenAI: GPT-5.3-Codex debuts with score 8.1
⚠️
28. JunNano Banana Pro: 0/5 on Scandinavian 5 days in a row
⚠️
28. JunAion-1.0: 0/5 on Scandinavian 3 days in a row
See all models we compare →

Guide

Guides for choosing the right AI

The benchmark shows what performs best right now. These guides explain how to use the results in practice.

Best AI for writing

Choose a model for email, reports and publishable content.

AI and GDPR for business

Checklist for privacy, business data and internal AI policy.

Cheap AI vs premium AI

When premium is worth it and when lower-cost models are enough.

ChatGPT alternatives

See when Claude, Gemini, Perplexity or others may fit better.

AI orchestrator

Route tasks to the model that fits the job best.