Answer: The models best suited for visuals like diagrams and screenshots are GPT-5.6 Luna and Claude Sonnet 4.6, which support multimodal input for visual reasoning tasks. Status: Confirmed Entry: tool/github-copilot/models/recommended-models-visuals Revision: 4 Digest: sha256:9a5854842fd63912 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:31:09Z Last changed: 2026-11-19T13:06:01Z (Model: — → GPT-5.6 Luna) Last verified: 2026-11-20T13:12:27Z Next check: 2026-11-21T13:12:27Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Model | GPT-5.6 Luna | [1] | 2026-11-20 Capability | multimodal input | [1] | 2026-11-20 Sources: [1] GitHub. "AI model comparison - GitHub Docs". https://docs.github.com/en/copilot/reference/ai-models/model-comparison Role: primary. Accessed: 2026-11-20T13:12:27Z Quote: "GPT-5.6 Luna Quick, cost-efficient responses for smaller coding tasks, and supports multimodal input for visual reasoning tasks." (Supports: Model) Quote: "These models support multimodal input and are well suited for front-end work or visual debugging." (Supports: Capability) Snapshot SHA-256: b06e95fe5027d0c99905bbb31710c537b511d43cd8e519c5e3cf3b5809ad99c5 (captured 2026-11-19T13:05:59Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-19T13:06:01Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:12:27Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:12:27Z Last attempt: 2026-11-20T13:12:27Z Notes and limitations: Extracted automatically from a single official source (section "Task: Working with visuals (diagrams, screenshots)"). Related: https://latestn.com/tool/github-copilot/models/sdk-byok How do I use my own API key (BYOK) with the GitHub Copilot SDK? https://latestn.com/tool/github-copilot/models/sdk-byok-no-github-auth How do I use BYOK with the GitHub Copilot SDK so no GitHub authentication is needed? https://latestn.com/tool/github-copilot/models/select-local-models How do I select local models in GitHub Copilot Fusion? https://latestn.com/tool/github-copilot/models/recommended-models-deep-reasoning Which GitHub Copilot models should I use for deep reasoning and debugging? https://latestn.com/tool/github-copilot/models/recommended-models-fast-tasks Which GitHub Copilot models are recommended for fast help with simple or repetitive tasks? https://latestn.com/tool/github-copilot/models/recommended-models-general-coding Which AI models does GitHub Copilot recommend for general-purpose coding and writing? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-19T13:06:01Z | changed | Model: — → GPT-5.6 Luna | [1] 2026-11-19T13:06:01Z | changed | Model 2: Claude Sonnet 4.6 → — | [1] 2026-11-19T13:06:01Z | changed | Model 1: GPT-5.6 Luna → — | [1] 2026-11-16T12:56:32Z | changed | Capability: — → multimodal input | [1] 2026-11-16T12:56:32Z | changed | Model 2: — → Claude Sonnet 4.6 | [1] 2026-11-16T12:56:32Z | changed | Model 1: — → GPT-5.6 Luna | [1] 2026-11-16T12:56:32Z | changed | Use case: Working with visuals (diagrams, screenshots) → — | [1] 2026-11-16T12:56:32Z | changed | Model: GPT-5.6 Luna → — | [1] 2026-11-14T13:10:39Z | changed | Use case: — → Working with visuals (diagrams, screenshots) | [1] 2026-11-14T13:10:39Z | changed | Model: — → GPT-5.6 Luna | [1] 2026-11-14T13:10:39Z | changed | Capability: multimodal input → — | [1] 2026-11-14T13:10:39Z | changed | Model 2: Claude Sonnet 4.6 → — | [1] 2026-11-14T13:10:39Z | changed | Model 1: GPT-5.6 Luna → — | [1] 2026-11-13T03:31:09Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/github-copilot/models/recommended-models-visuals/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/github-copilot/models/recommended-models-visuals POST: https://latestn.com/dispute/tool/github-copilot/models/recommended-models-visuals with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/github-copilot/models/recommended-models-visuals?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Which GitHub Copilot models work best with visuals like diagrams and screenshots? Revision 4, last verified 2026-11-20T13:12:27Z. https://latestn.com/tool/github-copilot/models/recommended-models-visuals (accessed 2026-11-21T09:52:40Z). @misc{LatestN_tool_github_copilot_models_recommended_models_visuals_r4, title = {Which GitHub Copilot models work best with visuals like diagrams and screenshots?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/github-copilot/models/recommended-models-visuals}}, note = {Revision 4; digest sha256:9a5854842fd63912; last verified 2026-11-20T13:12:27Z; accessed 2026-11-21T09:52:40Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/github-copilot/models/recommended-models-visuals