Quick takeaways

  • Compare models by workflow, not by leaderboard rank.
  • Long context, reasoning, speed, and cost all matter depending on the job.
  • Re-test model fit when the task changes or the vendor releases a new version.

A developer's introduction to large language models

Andrej Karpathy covers how large language models work, what they excel at, and how to think about choosing one.

How to compare models

Use a real task, the same input, and a simple rubric. For example, compare models on a customer research summary, code review note, or SEO outline. Look at correctness, clarity, structure, and cleanup required.

  1. Pick a task your team does weekly.
  2. Prepare the same input and prompt for each model.
  3. Score outputs on correctness, clarity, structure, and tone.
  4. Measure cost and speed if you plan to run the task at scale.
  5. Document the winner and why, then re-test quarterly.

Selection criteria

WritingPrioritize tone control, structure, and editing quality.
CodingPrioritize repository awareness, tool use, and safe diffs.
ResearchPrioritize source quality, citations, and fast iteration.
Long contextPrioritize document handling and memory across larger inputs.
MultimodalPrioritize image, document, or voice handling if your workflow needs it.
CostPrioritize affordability when the task is high-volume but low-risk.

Price tier matrix

API pricing varies by model strength and provider. This table gives a rough sense of where each family sits. For exact rates, see the AI model API pricing page.

TierTypical price / 1M tokensGood forExamples
Budget~$0.05 - $0.25High-volume, low-risk tasksQwen, DeepSeek-V3, Gemini Flash
Mid-range~$0.50 - $3.00Most daily workGPT-4o, Claude Sonnet, Gemini Pro
Premium~$10.00+Hard reasoning, agents, codingClaude Opus, OpenAI o-series

Use case matrix

Writing

General assistant model

Use for drafting, editing, and structured thinking.

Coding

Code-aware model

Use for repo changes, debugging, and code explanation.

Research

Source-heavy model

Use for summaries, citations, and decision support.

Creative

Multimodal model

Use for image, voice, or mixed-format tasks.

Best for specific jobs

Research

Best AI model for research

Models that handle citations, source synthesis, and deep-dive analysis.

Read guide
Long context

Best AI model for long context

Models that can process long documents, books, and large codebases.

Read guide
Local

Best local LLM

Self-hosted options for privacy, control, and cost at scale.

Read guide
Coding

Best AI model for coding

Top picks for repo work, debugging, and learning to code.

Read guide

Decision tree

Use this tree to narrow your choice:

  • Is the task about writing, editing, or reasoning? Start with a general assistant like GPT-4o or Claude Sonnet.
  • Is the task about code? Use a code-aware model or coding agent like Claude Code, Cursor, or Codex.
  • Does the task need long documents or many files? Prioritize context window and retrieval support.
  • Does the task need images, audio, or video? Use a multimodal model like Gemini or GPT-4o.
  • Is the task high-volume and low-risk? Consider a smaller, cheaper model or API tier.

Popular families

Explore the current model family pages

OpenAI

OpenAI GPT family

General-purpose models for writing, reasoning, voice, images, and coding.

Open family
Anthropic

Claude family

Writing, analysis, coding, and agentic workflows.

Open family
Google

Gemini family

Multimodal, Google-native, and voice-ready workflows.

Open family
xAI

Grok family

Live search, reasoning, multi-agent, and media generation.

Open family
DeepSeek

DeepSeek family

Reasoning, coding, and open-model experimentation.

Open family
Meta

Llama family

Open models for self-hosting and customization.

Open family
Mistral

Mistral family

Document intelligence, coding, and platform control.

Open family
Qwen

Qwen family

Multilingual, multimodal, safety, and translation workflows.

Open family
Note: Model availability and pricing change often. Verify current plans and feature sets on the official product pages before you commit to a stack.

Without AI vs. with AI

TaskWithout AIWith AI
Model choiceTeams pick models based on leaderboard hype or brand recognition.Models are chosen by use case, context length, speed, cost, and review needs.
LatencyLatency is guessed from marketing claims and benchmark tables.Latency is measured on real inputs at expected throughput and concurrency.
CostCost is ignored until the first big bill arrives.Per-token and per-request economics are modeled before scaling the workflow.
Context lengthLong documents are truncated or chunked without a strategy.The right context window and chunking approach are selected for the task.
QualityQuality is judged from public benchmarks alone.Teams score outputs on the same real task using a simple rubric and re-test quarterly.

FAQ

Which model is best for beginners?

The best beginner model is usually the one already integrated into your workflow and easy to review.

Should teams use multiple models?

Yes, if different workflows benefit from different strengths. Keep the stack small enough to govern.

How often should we re-test model fit?

Quarterly, or whenever a major version is released or your workflow changes significantly.

Do benchmarks matter?

Benchmarks give a rough signal, but your real task and review process matter more.

Should we self-host an open model?

Consider self-hosting when data residency, customization, or cost at scale is critical. It adds infrastructure and maintenance overhead.

How do we avoid model lock-in?

Use portable prompts, avoid proprietary features for core workflows, and test alternatives periodically.

Is the most powerful model always the best choice?

No. The best model balances capability, cost, speed, and the amount of review your use case can tolerate.

How do I compare models fairly?

Use the same prompt, input, and rubric across candidates; score correctness, structure, tone, cost, and latency.

Should I use one model or many?

Use one general model for simple work and route specialized tasks to models that excel at coding, reasoning, or long context.

How often should I re-evaluate model choice?

Re-test when the task changes, usage scales, or a vendor releases a new version that claims better performance.