Switchy
Open app

Best AI models for reasoning & research

Models tuned for step-by-step reasoning, math, and synthesis-heavy research tasks.

Research tasks reward models that reason step-by-step in the open and cite specific facts back to the source. The most expensive flagships still win here, especially when the trail of thought matters as much as the conclusion.

Switchy's picks

  1. 1
    Anthropic: Claude Opus 4.5

    Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

    anthropic200K context$5.00/Mtok in
  2. 2
    Anthropic: Claude Sonnet 4.5

    Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

    anthropic1000K context$3.00/Mtok in
  3. 3
    Google: Gemini 2.5 Pro Preview 06-05

    Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

    google1049K context$1.25/Mtok in
  4. 4
    OpenAI: GPT-4.1

    GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

    openai1048K context$2.00/Mtok in
  5. 5
    DeepSeek: R1

    DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

    deepseek64K context$0.70/Mtok in

Other llm models

Browse all tasks