Battle of the Models

Compare specific LLM models, context windows, and capabilities.

North Mini Code

Cohere

Intelligence Score 77/100

Model Popularity 0 votes

Context Window 256K Context

Pricing Model Free / Open

View Provider Analysis →

DEPRECATED

Google AI Studio

This model is no longer active/free — kept for reference.

Intelligence Score 96/100

Context Window 1M Context, 15 RPM

Pricing Model Free / Open

Model Popularity 0 votes

View Provider Analysis →

FINAL VERDICT

With an intelligence score of 96/100 vs 77/100, Gemini 3.1 Flash outperforms North Mini Code by 19 points.

Clear Winner: Significant performance advantage for Gemini 3.1 Flash.

HEAD-TO-HEAD

Feature	North Mini Code	Gemini 3.1 Flash
Context Window	256K Context	1M Context, 15 RPM
Architecture	Transformer	Transformer (Proprietary)
Est. MMLU Score	~70-74%	~92-95%
Release Date	2024	2026 (Expected)
Pricing Model	Free Tier	Free Tier
Rate Limit (RPM)	20 requests/minute	5-30 RPM (varies by model)
Daily Limit	-	Varies by model (Flash / Flash-Lite only; Pro models are paid)
Capabilities	No specific data	Thinking Multimodal
Performance Tier	B-Tier (Strong)	S-Tier (Elite)
Speed Estimate	⚡ Very Fast	⚡ Very Fast
Primary Use Case	💻 Code Generation	⚡ Fast Chat & Apps
Model Size	Undisclosed	~1.5T (estimated)
Limitations	Monthly quota shared across all models 1,000 API calls/month on free tier Commercial use restricted on free plan	Data used for training (Unpaid tier) Rate limits are enforced per minute/day No SLA for free tier
Key Strengths	Retrieval Augmented Generation (RAG) built-in Enterprise-grade models Embeddings and reranking models	Multimodal Capabilities Huge Context Window (up to 2M tokens) Fast Inference Speed