37 models · 11 labs · one decision

Find the right AI model, for every job

GPT-5, Claude, Gemini, GLM, Kimi, DeepSeek — the lineup keeps growing and they are not interchangeable. Whether you are coding, writing, researching, or just getting things done, this guide maps the frontier: side-by-side specs, real benchmarks, and plain-English guidance on which model fits which task.

Catalogued labs
ClaudeGPTGeminiGLMKimiDeepSeek+ windows to 10M tokens
Why it matters

Picking a model is a real decision — for anyone

Coder or writer, analyst or student, the same prompt can cost cents or dollars, fit or overflow, answer instantly or stall. Four axes decide most of it.

  • Cost
    947×
    Price swings are enormous

    Output token prices span 947× across the catalog. Pick wrong and a high-volume job costs an order of magnitude more than it should.

  • Context
    10M
    Context windows differ wildly

    From tight, cheap windows to 10M tokens. The right window depends on whether you feed in a paragraph or a whole book — or an entire codebase.

  • Openness
    17
    Open vs. closed weights

    17 tracked models ship open weights you can self-host for privacy and control — the rest are API-only. The trade-off shapes your setup.

  • Latency
    250 tps
    Latency is a feature

    Throughput ranges from deliberate reasoners to models pushing 250 tokens/sec. A live back-and-forth and an overnight batch want opposite ends of that scale.

Test yourself

Think you can call the right model?

The context quiz drops you into real, constrained scenarios — budget, latency, volume, privacy — and grades your pick against the trade-offs. Learn the reasoning, not just the answer.

Take the quiz14 scenarios · ~5 min
Scenario 1easy
A near-free pocket assistant for everyday questions

You're launching a free consumer app that answers quick everyday questions — recipe swaps, plain-English explanations, trip ideas, unit conversions. It's plain text, the quality bar is 'feels smart enough,' replies must stream back instantly, and with millions of tiny queries a day the cost per answer has to be almost nothing.

Which would you reach for?
  • GPT-5.4 nanoGPT
  • Gemini 3.1 Flash-LiteGemini
  • DeepSeek-V3.2DeepSeek
  • Claude Haiku 4.5Claude
By the numbers
Models tracked
37
Models trackedacross 11 labs
Output price / 1M
$0.19–$180
Output price / 1Ma 947× spread
Largest context
10M
Largest contexttokens in one call
Open-weight models
17
Open-weight modelsself-hostable
The labs

Every major lab, under one roof

11 labs across 3 countries — from frontier closed models to self-hostable open weights. We track them all, so you can weigh a Claude against a Kimi without opening sixteen tabs.

  • Anthropic
    Claude · 6 models
  • OpenAI
    GPT · 5 models
  • Alibaba Qwen
    Qwen · 4 models
  • DeepSeek
    DeepSeek · 4 models
  • Google DeepMind
    Gemini · 4 models
  • Mistral AI
    Mistral · 4 models
  • Moonshot AI
    Kimi · 3 models
  • Meta AI
    Llama · 2 models
  • xAI
    Grok · 2 models
  • Zhipu AI
    GLM · 2 models
  • MiniMax
    MiniMax · 1 model

Stop guessing. Start matching.

Compare any two models head-to-head, or browse the full catalog and filter to exactly what your task needs.