Skip to content

Commit 66d0d55

Browse files
docs-botdocs-bot
authored
Merge pull request #40033 from github/repo-sync
Repo sync
2 parents d183229 + 77e6676 commit 66d0d55

35 files changed

+550
-187
lines changed

‎assets/images/help/issues/issue-type.png

258 KB
Loading

‎assets/images/help/issues/sub-issue.png

118 KB
Loading

‎assets/images/help/projects-v2/example-board.png

374 KB
Loading

‎assets/images/help/projects-v2/example-roadmap.png

342 KB
Loading

‎assets/images/help/projects-v2/example-table.png

383 KB
Loading

‎content/copilot/reference/ai-models/model-comparison.md

Lines changed: 24 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -21,33 +21,37 @@ contentType: reference
2121
2222
### Recommended models by task
2323

24+
{% data reusables.copilot.grok-promo-period %}
25+
2426
Use this table to find a suitable model quickly, see more detail in the sections below.
2527

26-
| Model | Task area | Excels at (primary use case) | Additional capabilities | Further reading |
27-
|-------|-----------|-------------------------------|--------------------------|------------------|
28-
| {% data variables.copilot.copilot_gpt_41 %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode, vision | [{% data variables.copilot.copilot_gpt_41 %} model card](https://openai.com/index/gpt-4-1/)|
29-
| {% data variables.copilot.copilot_gpt_5_mini %} | Deep reasoning and debugging | Well-defined tasks and precise prompts | Reasoning | Not available |
30-
| {% data variables.copilot.copilot_gpt_5 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning | [{% data variables.copilot.copilot_gpt_5 %} model card](https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb52f/gpt5-system-card-aug7.pdf) |
31-
| {% data variables.copilot.copilot_o3 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning | [{% data variables.copilot.copilot_o3 %} model card](https://openai.com/index/o3-o4-mini-system-card/) |
32-
| {% data variables.copilot.copilot_o4_mini %} | Fast help with simple or repetitive tasks | Fast, reliable answers to lightweight coding questions | Lower latency | [{% data variables.copilot.copilot_o4_mini %} model card](https://openai.com/index/o3-o4-mini-system-card/) |
33-
| {% data variables.copilot.copilot_claude_opus_41 %} | Deep reasoning and debugging | Complex problem-solving challenges, sophisticated reasoning | Reasoning, vision | [{% data variables.copilot.copilot_claude_opus_41 %} model card](https://assets.anthropic.com/m/4c024b86c698d3d4/original/Claude-4-1-System-Card.pdf) |
34-
| {% data variables.copilot.copilot_claude_opus %} | Deep reasoning and debugging | Complex problem-solving challenges, sophisticated reasoning | Reasoning, vision | [{% data variables.copilot.copilot_claude_opus %} model card](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) |
35-
| {% data variables.copilot.copilot_claude_sonnet_35 %} | Fast help with simple or repetitive tasks | Quick responses for code, syntax, and documentation | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_35 %} model card](https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf) |
36-
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Deep reasoning and debugging | Structured reasoning across large, complex codebases | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_37 %} model card](https://assets.anthropic.com/m/785e231869ea8b3b/original/claude-3-7-sonnet-system-card.pdf) |
37-
| {% data variables.copilot.copilot_claude_sonnet_40 %} | Deep reasoning and debugging | Performance and practicality, perfectly balanced for coding workflows | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_40 %} model card](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) |
38-
| {% data variables.copilot.copilot_gemini_25_pro %} | Deep reasoning and debugging | Complex code generation, debugging, and research workflows | Reasoning, vision | [{% data variables.copilot.copilot_gemini_25_pro %} model card](https://storage.googleapis.com/model-cards/documents/gemini-2.5-pro.pdf) |
39-
| {% data variables.copilot.copilot_gemini_flash %} | Working with visuals (diagrams, screenshots) | Real-time responses and visual reasoning for UI and diagram-based tasks | Vision | [{% data variables.copilot.copilot_gemini_flash %} model card](https://storage.googleapis.com/model-cards/documents/gemini-2-flash.pdf) |
28+
| Model | Task area | Excels at (primary use case) | Additional capabilities | Further reading |
29+
|-------------------------------------------------------|-----------|-------------------------------|-------------------------|------------------|
30+
| {% data variables.copilot.copilot_gpt_41 %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode, vision | [{% data variables.copilot.copilot_gpt_41 %} model card](https://openai.com/index/gpt-4-1/)|
31+
| {% data variables.copilot.copilot_gpt_5_mini %} | Deep reasoning and debugging | Well-defined tasks and precise prompts | Reasoning, vision | Not available |
32+
| {% data variables.copilot.copilot_gpt_5 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning | [{% data variables.copilot.copilot_gpt_5 %} model card](https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb52f/gpt5-system-card-aug7.pdf) |
33+
| {% data variables.copilot.copilot_o3 %} | Deep reasoning and debugging | Multi-step problem solving and architecture-level code analysis | Reasoning | [{% data variables.copilot.copilot_o3 %} model card](https://openai.com/index/o3-o4-mini-system-card/) |
34+
| {% data variables.copilot.copilot_o4_mini %} | Fast help with simple or repetitive tasks | Fast, reliable answers to lightweight coding questions | Lower latency | [{% data variables.copilot.copilot_o4_mini %} model card](https://openai.com/index/o3-o4-mini-system-card/) |
35+
| {% data variables.copilot.copilot_claude_opus_41 %} | Deep reasoning and debugging | Complex problem-solving challenges, sophisticated reasoning | Reasoning, vision | [{% data variables.copilot.copilot_claude_opus_41 %} model card](https://assets.anthropic.com/m/4c024b86c698d3d4/original/Claude-4-1-System-Card.pdf) |
36+
| {% data variables.copilot.copilot_claude_opus %} | Deep reasoning and debugging | Complex problem-solving challenges, sophisticated reasoning | Reasoning, vision | [{% data variables.copilot.copilot_claude_opus %} model card](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) |
37+
| {% data variables.copilot.copilot_claude_sonnet_35 %} | Fast help with simple or repetitive tasks | Quick responses for code, syntax, and documentation | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_35 %} model card](https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf) |
38+
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Deep reasoning and debugging | Structured reasoning across large, complex codebases | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_37 %} model card](https://assets.anthropic.com/m/785e231869ea8b3b/original/claude-3-7-sonnet-system-card.pdf) |
39+
| {% data variables.copilot.copilot_claude_sonnet_40 %} | Deep reasoning and debugging | Performance and practicality, perfectly balanced for coding workflows | Agent mode, vision | [{% data variables.copilot.copilot_claude_sonnet_40 %} model card](https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf) |
40+
| {% data variables.copilot.copilot_gemini_25_pro %} | Deep reasoning and debugging | Complex code generation, debugging, and research workflows | Reasoning, vision | [{% data variables.copilot.copilot_gemini_25_pro %} model card](https://storage.googleapis.com/model-cards/documents/gemini-2.5-pro.pdf) |
41+
| {% data variables.copilot.copilot_gemini_flash %} | Working with visuals (diagrams, screenshots) | Real-time responses and visual reasoning for UI and diagram-based tasks | Vision | [{% data variables.copilot.copilot_gemini_flash %} model card](https://storage.googleapis.com/model-cards/documents/gemini-2-flash.pdf) |
42+
| {% data variables.copilot.copilot_grok_code %} | General-purpose coding and writing | Fast, accurate code completions and explanations | Agent mode, vision | [{% data variables.copilot.copilot_grok_code %} model card](https://data.x.ai/2025-08-20-grok-4-model-card.pdf)|
4043

4144
## Task: General-purpose coding and writing
4245

4346
Use these models for common development tasks that require a balance of quality, speed, and cost efficiency. These models are a good default when you don't have specific requirements.
4447

45-
| Model | Why it's a good fit |
46-
|-------|---------------------|
47-
| {% data variables.copilot.copilot_gpt_41 %} | Reliable default for most coding and writing tasks. Fast, accurate, and works well across languages and frameworks. |
48-
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Produces clear, structured output. Follows formatting instructions and maintains consistent style. |
49-
| {% data variables.copilot.copilot_gemini_flash %} | Fast and cost-effective. Well suited for quick questions, short code snippets, and lightweight writing tasks. |
50-
| {% data variables.copilot.copilot_o4_mini %} | Optimized for speed and cost efficiency. Ideal for real-time suggestions with low usage overhead. |
48+
| Model | Why it's a good fit |
49+
|-------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|
50+
| {% data variables.copilot.copilot_gpt_41 %} | Reliable default for most coding and writing tasks. Fast, accurate, and works well across languages and frameworks. |
51+
| {% data variables.copilot.copilot_claude_sonnet_37 %} | Produces clear, structured output. Follows formatting instructions and maintains consistent style. |
52+
| {% data variables.copilot.copilot_gemini_flash %} | Fast and cost-effective. Well suited for quick questions, short code snippets, and lightweight writing tasks. |
53+
| {% data variables.copilot.copilot_o4_mini %} | Optimized for speed and cost efficiency. Ideal for real-time suggestions with low usage overhead. |
54+
| {% data variables.copilot.copilot_grok_code %} | Specialized for coding tasks. Performs well on code generation, and debugging across multiple languages. |
5155

5256
### When to use these models
5357

‎content/copilot/reference/ai-models/model-hosting.md

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -63,3 +63,22 @@ Used for:
6363
To provide better service quality and reduce latency, {% data variables.product.github %} uses [prompt caching](https://cloud.google.com/vertex-ai/generative-ai/docs/data-governance#customer_data_retention_and_achieving_zero_data_retention).
6464

6565
When using {% data variables.copilot.copilot_gemini %} models, input prompts and output completions continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful or offensive content.
66+
67+
## xAI models
68+
69+
{% data reusables.copilot.grok-promo-period %}
70+
71+
{% data variables.copilot.copilot_grok_code %} is hosted by xAI when used in {% data variables.product.prodname_copilot %}.
72+
73+
xAI operates {% data variables.copilot.copilot_grok_code %} in {% data variables.product.prodname_copilot %} under a zero data retention API policy. This means xAI commits that user content (both inputs sent to the model and outputs generated by the model):
74+
75+
Will **not** be:
76+
* Logged for any purpose, including human review
77+
* Saved to disk or retained in any form, including as metadata
78+
* Accessible by xAI personnel
79+
80+
Will **only**:
81+
* Exist temporarily in RAM for the minimum time required to process and respond to each request
82+
* Be immediately deleted from memory once the response is delivered
83+
84+
When using xAI, input prompts and output completions continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful or offensive content.

0 commit comments

Comments
 (0)