> ## Documentation Index > Fetch the complete documentation index at: https://docs.tess.im/llms.txt > Use this file to discover all available pages before exploring further. # Grok 4.7 > Learn about Grok 4.7 improvements in coding, long-running agents, and professional work with extended context. Grok 4.7 is xAI's frontier model for **coding, agents, and professional work that requires hours of execution**. The new generation was trained to stay with difficult problems longer, check its own work more carefully, and manage extended context more effectively. In practice, the improvement appears when the objective does not end with an answer: investigating a repository, implementing and testing a change, turning data into a presentation, or producing a professional analysis with sources and validation criteria. | **Provider model** `grok-4.7` | **Context** 500K tokens | **Provider** xAI | **Input** Text + image | | :- | :- | :- | :- | | **Output** Text | **Provider reasoning** Low · Medium · High · XHigh | **Knowledge cutoff** May 2026 | **Provider tools** Functions · Web · X · Code | ## What changes in Grok 4.7 Grok 4.7 is not merely another post-training update on the previous generation. According to xAI, it uses a **new, larger base model**, underwent a longer reinforcement learning run, and was trained on a harder task mix weighted toward work that takes many hours to complete. This concentrates the progress in four areas: * **greater autonomy in long tasks:** maintains the objective and continues advancing through several execution cycles; * **self-verification:** reviews decisions and results before concluding; * **better extended-context use:** works across larger codebases, documents, and histories without losing the thread; * **more complete knowledge work:** improves the creation of documents, presentations, and analyses for professional domains. | | Grok 4.6 | Grok 4.7 | | - | - | - | | Base | Previous generation | **New, larger base model** | | Context | 500K tokens | 500K tokens | | Knowledge cutoff | February 2026 | **May 2026** | | Reasoning | Low · Medium · High · XHigh | Low · Medium · High · XHigh | | Focus | Coding, agents, and knowledge work | **Longer execution, self-verification, and extended context** | | Provider price below 200K | USD 2 input · USD 6 output / 1M tokens | **Same price** | ## What the benchmarks show In results published by xAI, Grok 4.7 improves over Grok 4.6 on every evaluation highlighted in the launch. The strongest gains appear in long-running coding, terminal work, electrical engineering, and professional tasks. | Benchmark | Grok 4.6 | Grok 4.7 | What it evaluates | | - | -: | -: | - | | CursorBench 4.0 | 40.4% | **46.3%** | Long-running coding in a real environment | | DeepSWE v1.1 | 65.2% | **71.0%**\* | Software engineering in repositories | | Terminal-Bench 4.0 | 20.3% | **38.0%** | Autonomous multi-step terminal work | | EEBench | 53.0% | **64.0%** | Electrical engineering | | AA Briefcase v1.1 | 1,546 | **1,657** | Multi-hour professional work | | Harvey Legal Agent | 15.8% | **19.6%** | Agentic legal tasks | | HealthBench Professional | 48.5% | **56.7%** | Professional clinical reasoning | \* The Grok 4.7 DeepSWE result was measured at High effort. > [!TIP] > > **The main signal is in the combination of results.** Grok 4.7 does not improve only at code generation: it advances in staying with a task, operating tools, reviewing the result, and turning the work into a usable deliverable. > [!NOTE] > > These benchmarks were published by xAI and depend on the harness, tools, reasoning level, and evaluation criteria. Use them as a comparative reference and validate the model in your workflow before changing a production configuration. ## An independent view from Artificial Analysis [Artificial Analysis](https://artificialanalysis.ai/models/grok-4-7) evaluated Grok 4.7 at XHigh on Intelligence Index v4.3.2, a composite of ten evaluations covering reasoning, coding, tool use, professional documents, and long context. | Independent metric | Grok 4.7 XHigh | Practical interpretation | | - | -: | - | | Intelligence Index | **46 points** | Well above the median of 24 among comparable models | | Output speed | **39.3 tokens/s** | Below the median of 72.5 tokens/s | | Cost per index task | **\$3.74** | Competitive for the intelligence delivered | | Tokens generated in the evaluation | **240 million** | Well above the median of 94 million | | Context | **500K tokens** | Suitable for documents, codebases, and extended histories | The result reinforces an important positioning: Grok 4.7 delivers **high intelligence at a competitive price**, but it is not optimized for short, fast answers. At XHigh, it was slower and much more verbose than the median—traits that can increase time and consumption on extended tasks. > [!TIP] > > To use the model efficiently, define the format, length limit, and completion criteria. Use XHigh when depth justifies the latency; for fast iterations, begin with a lower effort level. > [!NOTE] > > This is an independent Artificial Analysis evaluation. The figures represent the model at XHigh and depend on the methodology, provider, and test configuration. ## Where it creates the most value ### A software change that spans the repository The work starts with an expected behavior but requires locating the flow, understanding dependencies, editing different layers, running tests, and reviewing the diff. Grok 4.7 was trained to sustain this type of long execution and verify its own work more carefully. **Expected result:** implemented code, executed tests, explained decisions, and identified remaining risks. ### Dispersed data that must become an executive deliverable Reports, spreadsheets, documents, and instructions need to be combined into a presentation, memo, or recommendation. Here, the value lies in keeping evidence connected to the narrative and preserving delivery criteria throughout the process. **Expected result:** material ready for review, with traceable conclusions, clear structure, and explicit gaps. ### Specialized analysis that requires caution In legal, clinical, financial, or technical domains, speed without verification increases risk. Grok 4.7 can explore hypotheses, challenge evidence, and review inconsistencies before consolidating an analysis—with human validation for high-impact decisions. **Expected result:** grounded analysis, identified uncertainties, and next validation steps. ## How to apply it in Tess **1. Choose a workflow with real work** Prefer a task with files, tools, stages, and a verifiable result. Isolated questions do not reveal the gains in autonomy and self-verification. **2. Provide context without dumping everything** Include the repository, documents, criteria, and examples needed. Even with 500K tokens, irrelevant context increases cost and makes prioritization harder. **3. Define tools and boundaries** Enable only the necessary tools, state what may be changed, and require approval for irreversible actions. **4. Describe the completion criteria** Specify tests, required sources, final format, and checks that must occur before delivery. **5. Match reasoning to difficulty** Use lower levels for fast iteration and increase effort when the task requires investigation, complex coding, or comparison of hypotheses. ## Three playbooks to get started ### 1. Full-stack implementation with review **Input:** repository, expected behavior, project standards, and test commands.\ **Tools:** code, terminal, and test suite. ```text theme={null} Map the responsible flow before editing. Identify related frontend, backend, persistence, and tests. Implement the smallest coherent change, run the relevant validations, and review the diff for regressions. Conclude with a summary of changes, tests executed, and remaining risks. ``` **Done when:** the behavior works end to end and the relevant validations pass. ### 2. Executive report from multiple sources **Input:** documents, spreadsheets, brief, and target audience.\ **Tools:** file search, data analysis, and document generation. ```text theme={null} Cross-reference the sources and build a decision-oriented narrative. For each conclusion, record the evidence that supports it. Separate facts, interpretations, and gaps. Deliver an executive summary, key findings, risks, prioritized recommendations, and an appendix with the sources used. ``` **Done when:** a decision-maker can review the document and every important conclusion is traceable. ### 3. Technical investigation with self-verification **Input:** problem, available evidence, constraints, and safety criteria.\ **Tools:** search, files, terminal, and domain-specific tools. ```text theme={null} Form competing hypotheses and test each against the evidence. Record what was rejected and why. Before concluding, perform a separate review for contradictions, weak sources, and unverified steps. Do not take irreversible actions without explicit approval. ``` **Done when:** evidence supports the conclusion, uncertainties are explicit, and the validation plan is defined. ## Limitations and best practices * The model's native knowledge cutoff is May 2026; use search for later facts. * Extended context does not replace information selection: send only relevant content. * Tools available from the provider may depend on the Tess configuration and enabled integrations. * Long tasks consume more time and tokens; use a lighter model for simple answers and transformations. * Review code, numbers, citations, and deliverables before publishing or running in production. * Keep human approval for legal, clinical, financial, security, or other high-impact decisions. See also: [Models and Costs](/en/models-and-cost) · [Grok 4.7 official documentation](https://docs.x.ai/developers/grok-4-7) · [Introducing Grok 4.7](https://x.ai/news/grok-4-7). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.