Skip to main content

Large Language Models

Who is winning the race to the bottom?

ProviderModelOpenStrengths
AnthropicClaude 3.7AI coding, creative reasoning
DeepSeekR1 V3Scientific research, cost
ElevenLabsTurbo v2.5Voice cloning, TTS
GoogleGemini 2.0Multimodal, deep research
MetaLlamaOpen source ecosystem
Nous ResearchDecentralised models
OpenAIGPT-4o / o3Broad ecosystem, agents
PerplexitySearch-native reasoning
QwenQwen 2.5Multilingual, open source
XAIGrokReal-time data, image gen

For modality capabilities — voice, image, video — see AI Modalities.

The market commoditises fast. Model selection matters less than prompting capability — knowing how to direct whichever model you use.

Model Selection

Review your Platform Stack regularly.

Gain maximum leverage by focusing on one critical job to be done at a time.

  1. Identify a recurring need
  2. Find the best tool — cost, speed, accuracy
  3. Master functionality
  4. Glue to workflows

If the tool does not exist, investigate building it.

Subject Expertise

  • Prompting — The capability that transfers across all models
  • Text Prompts — Copy-paste templates and provider guides
  • Visual Prompting — Image and video prompt structure
  • AI Agents — AI agents and the jobs they perform
  • AI Coding — Best AI coding tools and strategies

Context