For deep reasoning or complex coding challenges, try o3, GPT-4.5, or Claude 3.

7
GitHub Docs Version: Free, Pro, & Team Search GitHub Docs Sonnet.
GitHub Copilot / Use GitHub Copilot / AI models / Choose the right AI model
For multimodal inputs and real-time performance, try Gemini 2.0 Flash or GPT-4o.
You can click a model name in the list below to jump to a detailed overview of its strengths
and use cases.
Choosing the right AI model for your task GPT-4o
GPT-4.1
Compare available AI models in Copilot Chat and choose In this article GPT-4.5
the best model for your task. Comparison of AI models for
GitHub Copilot
o1
o3
GPT-4o o3-mini
Comparison of AI models for GitHub Copilot GPT-4.1
GPT-4.5
o4-mini
Claude 3.5 Sonnet
GitHub Copilot supports multiple AI models with different capabilities. The model you o1 Claude 3.7 Sonnet
choose affects the quality and relevance of responses in Copilot Chat and code o3 Gemini 2.0 Flash
completions. Some models offer lower latency, while others offer fewer hallucinations or o3-mini Gemini 2.5 Pro
better performance on specific tasks. o4-mini
This article helps you compare the available models, understand the strengths of each Claude 3.5 Sonnet Note
model, and choose the model that best fits your task. For guidance across different models Claude 3.7 Sonnet Different models have different premium request multipliers, which can affect how
using real-world tasks, see Comparing AI models using different tasks. Gemini 2.0 Flash much of your monthly usage allowance is consumed. For details, see About premium
Gemini 2.5 Pro requests.
The best model depends on your use case:
Further reading
For balance between cost and performance, try GPT-4.1 or Claude 3.7 Sonnet.
For fast, low-cost support for basic tasks, try o4-mini or Claude 3.5 Sonnet. GPT-4o

OpenAI GPT-4o is a multimodal model that supports text and images. It responds in real Task Description Why GPT-4o is a good fit
time and works well for lightweight development tasks and conversational prompts in
Copilot Chat. Bug investigation Get a quick explanation or Provides fast diagnostic insight.
Compared to previous models, GPT-4o improves performance in multilingual contexts and suggestion for an error.
demonstrates stronger capabilities when interpreting visual content. It delivers GPT-4 Code snippet generation Generate small, reusable pieces Delivers high-quality results
Turbo–level performance with lower latency and cost, making it a good default choice for of code. quickly.
many common developer tasks.
For more information about GPT-4o, see OpenAI's documentation. Multilingual prompts Work with non-English prompts Improved multilingual
or identifiers. comprehension.
Use cases Image-based questions Ask about a diagram or
screenshot (where image input
Supports visual reasoning.
GPT-4o is a strong default choice for common development tasks that benefit from speed, is supported).
responsiveness, and general-purpose reasoning. If you're working on tasks that require
broad knowledge, fast iteration, or basic code understanding, GPT-4o is likely the best
model to use. Alternative options
The following table summarizes when an alternative model may be a better choice:
Strengths
The following table summarizes the strengths of GPT-4o: Task Description Why another model may be
better
Task Description Why GPT-4o is a good fit Multi-step reasoning or Design complex logic or break GPT-4.5 or Claude 3.7 Sonnet
algorithms down multi-step problems. provide better step-by-step
Code explanation Understand what a block of Fast and accurate explanations. thinking.
code does or walk through
logic. Complex refactoring Refactor large codebases or GPT-4.5 handles context and
update multiple interdependent code dependencies more
Code commenting and Generate or refine comments Writes clear, concise files. robustly.
documentation and documentation. explanations.
Task Description Why another model may be general-purpose reasoning. If you're working on tasks that require broad knowledge, fast
better iteration, or basic code understanding, GPT-4.1 makes large improvements over GPT-4o.
System review or architecture Analyze structure, patterns, or Claude 3.7 Sonnet or GPT-4.5 Strengths
architectural decisions in depth. offer deeper analysis.
The following table summarizes the strengths of GPT-4.1:
GPT-4.1 Task Description Why GPT-4.1 is a good fit
Note Code explanation Understand what a block of Fast and accurate explanations.
code does or walk through
GPT-4.1 in Copilot Chat is currently in public preview and subject to change. logic.
OpenAI’s latest model, GPT-4.1, is now available in GitHub Copilot and GitHub Models, Code commenting and Generate or refine comments Writes clear, concise
bringing OpenAI’s newest model to your coding workflow. This model outperforms GPT-4o documentation and documentation. explanations.
across the board, with major gains in coding, instruction following, and long-context Bug investigation Get a quick explanation or Provides fast diagnostic insight.
understanding. It has a larger context window and features a refreshed knowledge cutoff of suggestion for an error.
June 2024.
OpenAI has optimized GPT-4.1 for real-world use based on direct developer feedback about: Code snippet generation Generate small, reusable pieces Delivers high-quality results
frontend coding, making fewer extraneous edits, following formats reliably, adhering to of code. quickly.
response structure and ordering, consistent tool usage, and more. This model is a strong Multilingual prompts Work with non-English prompts Improved multilingual
default choice for common development tasks that benefit from speed, responsiveness, and or identifiers. comprehension.
general-purpose reasoning.

Use cases Alternative options

GPT-4.1 is a revamped version of OpenAI's GPT-4o model. This model is a strong default
choice for common development tasks that benefit from speed, responsiveness, and

Task Description Why another model may be GPT-4.5 is a good choice for tasks that involve multiple steps, require deeper code
better comprehension, or benefit from a conversational model that handles nuance well.
Multi-step reasoning or Design complex logic or break GPT-4.5 or Claude 3.7 Sonnet Strengths
algorithms down multi-step problems. provide better step-by-step
thinking. The following table summarizes the strengths of GPT-4.5:
Complex refactoring Refactor large codebases or GPT-4.5 handles context and
update multiple interdependent code dependencies more Task Description Why GPT-4.5 is a good fit
files. robustly.
Code documentation Draft README files, or technical Generates clear, context-rich
System review or architecture Analyze structure, patterns, or Claude 3.7 Sonnet or GPT-4.5 explanations. writing with minimal editing.
architectural decisions in depth. offer deeper analysis.
Complex code generation Write full functions, classes, or Provides better structure,
multi-file logic. consistency, and fewer logic
errors.
GPT-4.5
Bug investigation Trace errors or walk through Maintains state and offers
OpenAI GPT-4.5 improves reasoning, reliability, and contextual understanding. It works well multi-step issues. reliable reasoning across steps.
for development tasks that involve complex logic, high-quality code generation, or
interpreting nuanced intent. Decision-making prompts Weigh pros and cons of Provides balanced,
libraries, patterns, or contextualized reasoning.
Compared to GPT-4o, GPT-4.5 produces more consistent results for multi-step reasoning, architecture.
long-form content, and complex problem-solving. It may have slightly higher latency and
costs than GPT-4o and other smaller models.
For more information about GPT-4.5, see OpenAI's documentation. Alternative options
The following table summarizes when an alternative model may be a better choice:
Use cases
Task Description Why another model may be Task Description Why o1 is a good fit
better
Code optimization Analyze and improve Excels at deep reasoning and
High-speed iteration Rapid back-and-forth prompts GPT-4o responds faster with performance-critical or identifying non-obvious
or code tweaks. similar quality for lightweight algorithmic code. improvements.
tasks.
Debugging complex systems Isolate and fix performance Provides step-by-step analysis
Cost-sensitive scenarios Tasks where performance-to- GPT-4o or o4-mini are more bottlenecks or multi-file issues. and high reasoning accuracy.
cost ratio matters. cost-effective.
Structured code generation Generate reusable functions, Supports function calling and
typed outputs, or structured structured output natively.
o1 responses.
Analytical summarization Interpret logs, benchmark Translates raw data into clear,
OpenAI o1 is an older reasoning model that supports complex, multi-step tasks and deep results, or code behavior. actionable insights.
logical reasoning to find the best solution.
Refactoring code Improve maintainability and Applies deliberate and context-
For more information about o1, see OpenAI's documentation. modularity of existing systems. aware suggestions.

Use cases Alternative options

o1 is a good choice for tasks that require deep logical reasoning. Its ability to reason through The following table summarizes when an alternative model may be a better choice:
complex logic enables Copilot to break down problems into clear, actionable steps. This
makes o1 particularly well-suited for debugging. Its internal reasoning can extend beyond
the original prompt to explore the broader context of a problem and can uncover edge cases Task Description Why another model may be
or root causes that weren’t explicitly mentioned. better
Quick iterations Rapid back-and-forth prompts GPT-4o or Gemini 2.0 Flash
Strengths or code tweaks. responds faster for lightweight
tasks.
The following table summarizes the strengths of o1:

Task Description Why another model may be Task Description Why o3 is a good fit
better
Code optimization Analyze and improve Excels at deep reasoning and
Cost-sensitive scenarios Tasks where performance-to- o4-mini or Gemini 2.0 Flash are performance-critical or identifying non-obvious
cost ratio matters. more cost-effective for basic algorithmic code. improvements.
use cases.
Debugging complex systems Isolate and fix performance Provides step-by-step analysis
bottlenecks or multi-file issues. and high reasoning accuracy.
o3 Structured code generation Generate reusable functions, Supports function calling and
typed outputs, or structured structured output natively.
Note responses.
o3 in Copilot Chat is currently in public preview and subject to change. Analytical summarization Interpret logs, benchmark Translates raw data into clear,
results, or code behavior. actionable insights.
OpenAI o3 is the most capable reasoning model in the o-series. It is ideal for deep coding
workflows and complex, multi-step tasks. For more information about o3, see OpenAI's Refactoring code Improve maintainability and Applies deliberate and context-
documentation. modularity of existing systems. aware suggestions.

Use cases Alternative options

o3 is a good choice for tasks that require deep logical reasoning. Its ability to reason through The following table summarizes when an alternative model may be a better choice:
complex logic enables Copilot to break down problems into clear, actionable steps. This
makes o3 particularly well-suited for debugging. Its internal reasoning can extend beyond Task Description Why another model may be
the original prompt to explore the broader context of a problem and can uncover edge cases better
or root causes that weren’t explicitly mentioned.
Quick iterations Rapid back-and-forth prompts GPT-4o or Gemini 2.0 Flash
or code tweaks. responds faster for lightweight
Strengths tasks.
The following table summarizes the strengths of o3:
Task Description Why another model may be Task Description Why o3-mini is a good fit
better
Real-time code suggestions Write or extend basic functions Responds quickly with
Cost-sensitive scenarios Tasks where performance-to- o4-mini or Gemini 2.0 Flash are and utilities. accurate, concise suggestions.
cost ratio matters. more cost-effective for basic
use cases. Code explanation Understand what a block of Fast, accurate summaries with
code does or walk through clear language.
logic.
o3-mini Learn new concepts Ask questions about Offers helpful, accessible
programming concepts or explanations with quick
OpenAI o3-mini is a fast, cost-effective reasoning model designed to deliver coding patterns. feedback.
performance while maintaining lower latency and resource usage. o3-mini outperforms o1
on coding benchmarks with response times that are comparable to o1-mini. Copilot is Quick prototyping Try out small ideas or test Fast, low-latency responses for
configured to use OpenAI's "medium" reasoning effort. simple code logic quickly. iterative feedback.
For more information about o1, see OpenAI's documentation.
Alternative options
Use cases The following table summarizes when an alternative model may be a better choice:
o3-mini is a good choice for developers who need fast, reliable answers to simple or
repetitive coding questions. Its speed and efficiency make it ideal for lightweight Task Description Why another model may be
development tasks. better
Deep reasoning tasks Multi-step analysis or GPT-4.5 or o1 provide more
Strengths architectural decisions. structured, thorough reasoning.
The following table summarizes the strengths of o3-mini: Creative or long-form tasks Writing docs, refactoring across o3-mini is less expressive and
large codebases. structured than larger models.

Task Description Why another model may be Task Description Why o4-mini is a good fit
better
Real-time code suggestions Write or extend basic functions Responds quickly with
Complex code generation Write full functions, classes, or Larger models handle and utilities. accurate, concise suggestions.
multi-file logic. complexity and structure more
reliably. Code explanation Understand what a block of Fast, accurate summaries with
code does or walk through clear language.
logic.
o4-mini Learn new concepts Ask questions about Offers helpful, accessible
programming concepts or explanations with quick
Note patterns. feedback.
o4-mini in Copilot Chat is currently in public preview and subject to change. Quick prototyping Try out small ideas or test Fast, low-latency responses for
simple code logic quickly. iterative feedback.
OpenAI o4-mini is the most efficient model in the o-series. It is a cost-effective reasoning
model designed to deliver coding performance while maintaining lower latency and resource
usage. Alternative options
For more information about o4, see OpenAI's documentation. The following table summarizes when an alternative model may be a better choice:
Use cases Task Description Why another model may be
better
o4-mini is a good choice for developers who need fast, reliable answers to simple or
repetitive coding questions. Its speed and efficiency make it ideal for lightweight Deep reasoning tasks Multi-step analysis or GPT-4.5 or o3 provide more
development tasks. architectural decisions. structured, thorough reasoning.
Creative or long-form tasks Writing docs, refactoring across o4-mini is less expressive and
Strengths large codebases. structured than larger models.
The following table summarizes the strengths of o4-mini:
Task Description Why another model may be Task Description Why Claude 3.5 Sonnet is a
better good fit
Complex code generation Write full functions, classes, or Larger models handle Code explanation Understand what a block of Fast and accurate explanations.
multi-file logic. complexity and structure more code does or walk through
reliably. logic.
Code commenting and Generate or refine comments Writes clear, concise
Claude 3.5 Sonnet documentation and documentation. explanations.
Quick language questions Ask syntax, idiom, or feature- Offers fast and accurate
Claude 3.5 Sonnet is a fast and cost-efficient model designed for everyday developer tasks. specific questions. explanations.
While it doesn't have the deeper reasoning capabilities of Claude 3.7 Sonnet, it still performs
well on coding tasks that require quick responses, clear summaries, and basic logic. Code snippet generation Generate small, reusable pieces Delivers high-quality results
of code. quickly.
For more information about Claude 3.5 Sonnet, see Anthropic's documentation. For more
information on using Claude in Copilot, see Using Claude Sonnet in Copilot Chat.
Alternative options
Use cases The following table summarizes when an alternative model may be a better choice:
Claude 3.5 Sonnet is a good choice for everyday coding support—including writing
documentation, answering language-specific questions, or generating boilerplate code. It Task Description Why another model may be
offers helpful, direct answers without over-complicating the task. If you're working within better
cost constraints, Claude 3.5 Sonnet is recommended as it delivers solid performance on Multi-step reasoning or Design complex logic or break GPT-4.5 or Claude 3.7 Sonnet
many of the same tasks as Claude 3.7 Sonnet, but with significantly lower resource usage. algorithms down multi-step problems. provide better step-by-step
thinking.
Strengths Complex refactoring Refactor large codebases or GPT-4.5 or Claude 3.7 Sonnet
The following table summarizes the strengths of Claude 3.5 Sonnet: update multiple interdependent handle context and code
files. dependencies more robustly.

Task Description Why another model may be Task Description Why Claude 3.7 Sonnet is a
better good fit
System review or architecture Analyze structure, patterns, or Claude 3.7 Sonnet or GPT-4.5 Multi-file refactoring Improve structure and Handles multi-step logic and
architectural decisions in depth. offer deeper analysis. maintainability across large retains cross-file context.
codebases.

Claude 3.7 Sonnet Architectural planning Support mixed task complexity, Fine-grained “thinking” controls
from small queries to strategic adapt to the scope of each
work. task.
Claude 3.7 Sonnet is Anthropic's most advanced model to date. Claude 3.7 Sonnet is a
powerful model that excels in development tasks that require structured reasoning across Feature development Build and implement Supports tasks with structured
large or complex codebases. Its hybrid approach to reasoning responds quickly when functionality across frontend, reasoning and reliable
needed, while still supporting slower step-by-step analysis for deeper tasks. backend, and API layers. completions.
For more information about Claude 3.7 Sonnet, see Anthropic's documentation. For more Algorithm design Design, test, and optimize Balances rapid prototyping with
information on using Claude in Copilot, see Using Claude Sonnet in Copilot Chat. complex algorithms. deep analysis when needed.
Analytical insights Combine high-level summaries Hybrid reasoning lets the model
Use cases with deep dives into code
behavior.
shift based on user needs.
Claude 3.7 Sonnet excels across the software development lifecycle, from initial design to
bug fixes, maintenance to optimizations. It is particularly well-suited for multi-file refactoring
or architectural planning, where understanding context across components is important. Alternative options
The following table summarizes when an alternative model may be a better choice:
Strengths
The following table summarizes the strengths of Claude 3.7 Sonnet:
Task Description Why another model may be Gemini 2.0 Flash supports image input so that developers can bring visual context into tasks
better like UI inspection, diagram analysis, or layout debugging. This makes Gemini 2.0 Flash
particularly useful for scenarios where image-based input enhances problem-solving, such
Quick iterations Rapid back-and-forth prompts GPT-4o responds faster for as asking Copilot to analyze a UI screenshot for accessibility issues or to help understand a
or code tweaks. lightweight tasks. visual bug in a layout.
Cost-sensitive scenarios Tasks where performance-to- o4-mini or Gemini 2.0 Flash are
cost ratio matters. more cost-effective for basic Strengths
use cases. Claude 3.5 Sonnet is
cheaper, simpler, and still The following table summarizes the strengths of Gemini 2.0 Flash:
advanced enough for similar
tasks. Task Description Why Gemini 2.0 Flash is a
good fit
Lightweight prototyping Rapid back-and-forth code Claude 3.7 Sonnet may over-
iterations with minimal context. engineer or apply unnecessary Code snippet generation Generate small, reusable pieces Delivers high-quality results
complexity. of code. quickly.
Design feedback loops Get suggestions from sketches, Supports visual reasoning.
Gemini 2.0 Flash diagrams, or visual drafts
Image-based analysis Ask about a diagram or Supports visual reasoning.
Gemini 2.0 Flash is Google’s high-speed, multimodal model optimized for real-time, screenshot (where image input
interactive applications that benefit from visual input and agentic reasoning. In Copilot Chat, is supported).
Gemini 2.0 Flash enables fast responses and cross-modal understanding.
Front-end prototyping Build and test UIs or workflows Supports multimodal reasoning
For more information about Gemini 2.0 Flash, see Google's documentation. For more involving visual elements and lightweight context.
information on using Gemini in Copilot, see Using Gemini in Copilot Chat.
Bug investigation Get a quick explanation or Provides fast diagnostic insight.
suggestion for an error.
Use cases

analyzing data and generating insights across a wide range of disciplines. Its long-context
Alternative options capabilities allow it to manage and understand extensive documents or datasets effectively.
The following table summarizes when an alternative model may be a better choice: Gemini 2.5 Pro is a strong choice for developers needing a powerful model.
Task Description Why another model may be
better
Strengths
The following table summarizes the strengths of Gemini 2.5 Pro:
Multi-step reasoning or Design complex logic or break GPT-4.5 or Claude 3.7 Sonnet
algorithms down multi-step problems. provide better step-by-step Task Description Why Gemini 2.5 Pro is a good
thinking. fit
Complex refactoring Refactor large codebases or GPT-4.5 handles context and Complex code generation Write full functions, classes, or Provides better structure,
update multiple interdependent code dependencies more multi-file logic. consistency, and fewer logic
files. robustly. errors.
Debugging complex systems Isolate and fix performance Provides step-by-step analysis
Gemini 2.5 Pro bottlenecks or multi-file issues. and high reasoning accuracy.
Gemini 2.5 Pro is Google's latest AI model, designed to handle complex tasks with advanced Scientific research Analyze data and generate Supports complex analysis with
reasoning and coding capabilities. It also works well for heavy research workflows that insights across scientific heavy researching capabilities.
disciplines.
require long-context understanding and analysis.
For more information about Gemini 2.5 Pro, see Google's documentation. For more Long-context processing Analyze extensive documents, Handles long-context inputs
information on using Gemini in Copilot, see Using Gemini in Copilot Chat. datasets, or codebases. effectively.

Use cases Alternative options

Gemini 2.5 Pro is well-suited for advanced coding tasks, such as developing complex The following table summarizes when an alternative model may be a better choice:
algorithms or debugging intricate codebases. It can assist with scientific research by
Task Description Why another model may be
better
Cost-sensitive scenarios Tasks where performance-to- o4-mini or Gemini 2.0 Flash are
cost ratio matters. more cost-effective for basic
use cases.

Further reading
Comparing AI models using different tasks
Changing the AI model for Copilot Chat
Changing the AI model for Copilot code completion
Legal
© 2025 GitHub, Inc. Terms Privacy Status Pricing Expert services Blog