The Model Landscape

Layer 1 · Intuition

The Model Landscape

A map of today's major LLM families and the axes that actually distinguish them.

5 min read40 XP

GPT-4 / GPT-4o

OpenAI, closed

Claude

Anthropic, closed

Gemini

Google, closed

Llama

Meta, open weights

Mistral/Mixtral

Mistral, open weights

DeepSeek

DeepSeek, open weights

Qwen

Alibaba, open weights

Gemma

Google, open weights

A snapshot of major model families — this list ages fast, the axes below don't.

The specific names on top of any 'best model' leaderboard change every few months, so memorizing today's winner is a losing game. What's stable is the set of *axes* along which these models actually differ, and understanding those axes lets you evaluate whatever model comes out next without starting from scratch.

  • Open weights vs. closed/API-only — can you download and run the model yourself, or only call it through a paid API?
  • Dense vs. Mixture-of-Experts (MoE) — does every token pass through the whole network, or only a routed subset of specialized sub-networks?
  • Parameter count and training compute — rough proxies for capability, though far from perfect ones today.
  • Context window — how many tokens of input the model can attend to at once.
  • Modality — text-only, or natively multimodal (text, image, audio, video)?

Closed, API-only models (GPT-4-class, Claude, Gemini) are typically the largest and most capable at launch, updated frequently, and require no infrastructure to use — but you're dependent on a vendor's pricing, uptime, and policies, and can't inspect or modify the weights. Open-weight models trade some peak capability for control: you can fine-tune them, run them privately, and inspect (though not fully understand) what's inside.

  • Bigger dense models cost more to serve per token than smaller or MoE models of similar capability.
  • Context window claims ("1M tokens!") don't always translate to actually using that context well — see the evaluation star for why raw specs mislead.
  • Multimodal-native models are trained from the start on mixed text/image/audio data, rather than bolting a vision encoder onto a text-only model after the fact.

Check your understanding

4 questions · answer all to submit

  1. 1.Why is relying on the current 'best' model designation a potentially short-sighted strategy for an LLM engineer?

  2. 2.What does 'open weights' typically signify in the context of LLMs, differentiating it from full open-source software?

  3. 3.What is a primary trade-off when choosing between a closed, API-only model and an open-weight model?

  4. 4.Which long-term trend regarding LLMs is considered more significant than any single model's current ranking?