xAI model product
Grok 4.7
7 is an LLM from xAI for long-running agents, coding, knowledge work, and visual projects.
Updated Nov 11, 2026. Default version: Grok 4.7
LLMBoard Score68.4Grok 4.7
Coverage20%9 benchmark families
Context window500KTokens
Official input price$2xAI API
Grok 4.7 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 4.7 Benchmark Results
Benchmark scores for Grok 4.7.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkHarvey LAB (Vals) | Score19.60% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVirology Capabilities Test | Score63.00% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBixBench MCQ | Score88.40% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCADGenBench | Score44.40% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCathedralBench | Score29.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCVE-Bench | Score36.60% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkEEBench | Score66.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGDPval (Elo) | Score1,695.00 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLAB-Bench Practical | Score76.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLatchBio Capabilities v1.0 | Score44.50% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkProtocolQA Open-Ended | Score70.40% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWMDP-Bio | Score88.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWMDP-Chem | Score84.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWMDP-Cyber | Score88.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHarvey's Legal Agent Benchmark | Score19.60% | Rank02 | Participants5 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkCursorBench 4.0 | Score46.30% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAA-Briefcase v1.1 | Score1,657.00 points | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkSWE-Marathon | Score46.00% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score95.68 score | Rank06 | Participants43 | Percentile88.10% | EvidenceB | EvaluatedN/A |
| BenchmarkFrontierSWE V2 | Score29.00% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score7.20% | Rank08 | Participants44 | Percentile83.72% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score5.46% | Rank08 | Participants43 | Percentile83.33% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.92% | Rank08 | Participants43 | Percentile83.33% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability | Score9.55% | Rank08 | Participants43 | Percentile83.33% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score2.65% | Rank09 | Participants43 | Percentile80.95% | EvidenceA | Evaluated |
| BenchmarkLiveBench instruction (2026-06-25) | Score75.28 score | Rank09 | Participants43 | Percentile80.95% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Webdev | Score1,639.36 rating | Rank11 | Participants109 | Percentile90.74% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score2.79% | Rank12 | Participants43 | Percentile73.81% | EvidenceA | Evaluated |
| BenchmarkCyberGym | Score80.30% | Rank14 | Participants23 | Percentile40.91% | EvidenceC | Evaluated |
| BenchmarkHealthBench Professional | Score56.70% | Rank18 | Participants22 | Percentile19.05% | EvidenceC | Evaluated |
Grok 4.7 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent bash recovery steps | Categoryoverall | Rank08 | Rating / score0.07 | VotesN/A | Observations41.9K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank08 | Rating / score0.05 | VotesN/A | Observations9.1K | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank08 | Rating / score0.01 | VotesN/A | Observations3.3M | Result date |
| Arenaagent bash reliability | Categoryoverall | Rank08 | Rating / score0.10 | VotesN/A | Observations261.2K | Result date |
| Arenaagent | Categoryoverall | Rank09 | Rating / score0.03 | VotesN/A | Observations3.7M | Result date |
| Arenawebdev | Categorywebdev-react | Rank10 | Rating / score1,662.25 | Votes4,806 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank11 | Rating / score1,639.36 | Votes7,816 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank11 | Rating / score1,639.36 | Votes7,816 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank12 | Rating / score0.03 | VotesN/A | Observations4.7K | Result date |
| Arenawebdev | Categorywebdev-html | Rank13 | Rating / score1,633.76 | Votes1,288 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank14 | Rating / score1,590.00 | Votes1,912 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank23 | Rating / score-0.02 | VotesN/A | Observations98.5K | Result date |
| Arenavision style control | Categoryhomework | Rank24 | Rating / score1,307.44 | Votes889 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank34 | Rating / score1,291.64 | Votes889 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank35 | Rating / score1,478.88 | Votes540 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank36 | Rating / score1,466.78 | Votes310 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank37 | Rating / score1,283.85 | Votes1,520 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank40 | Rating / score1,262.87 | Votes4,162 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank42 | Rating / score1,248.92 | Votes6,181 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank43 | Rating / score1,457.72 | Votes974 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank43 | Rating / score1,249.27 | Votes2,078 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank48 | Rating / score1,228.80 | Votes570 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank49 | Rating / score1,469.80 | Votes1,176 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank51 | Rating / score1,220.29 | Votes237 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank53 | Rating / score1,459.32 | Votes1,482 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank53 | Rating / score1,257.15 | Votes1,520 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank53 | Rating / score1,271.61 | Votes308 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank54 | Rating / score1,474.00 | Votes761 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank54 | Rating / score1,413.12 | Votes309 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank56 | Rating / score1,442.29 | Votes863 | ObservationsN/A | Result date |
Grok 4.7 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $6 output per 1M
- Official provider
- xAI
- Lowest third-party
- From $1.6 input, $4.8 output per 1M via Prime Inference
- Tracked offerings
- 27
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPrime Inference | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$1.6 | Output / 1M$4.8 | Context500K | Updated |
| ProviderVercel AI Gateway | Provider model IDspacexai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderKilo Gateway | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderOpenRouter | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderxAI | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderOpenCode Go | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderNanoGPT | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderCrossModel | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgrok-4-7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context524.3K | Updated |
| ProviderGitHub Copilot | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderMerge Gateway | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderEden AI | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderOfox | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderOpenCode | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderAIHubMix | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| Provider302.AI | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderTempr Gateway | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderRequesty | Provider model IDgrok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderVertex | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context524.3K | Updated |
| ProviderNEAR AI Cloud | Provider model IDx-ai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderCommandCode | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderPerplexity Agent | Provider model IDxai/grok-4.7 | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context500K | Updated |
| ProviderVenice AI | Provider model IDgrok-4-7 | Regionglobal | Input / 1M$2.27 | Output / 1M$6.8 | Context500K | Updated |
| ProviderNeon | Provider model IDgrok-4-7 | Regionglobal | Input / 1M$2.5 | Output / 1M$7.5 | Context500K | Updated |
Grok 4.7 Runtime Performance
Provider-specific output speed and catalog latency for Grok 4.7. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 4.7 Specifications
Technical details for the model's default version.
- Version
- Grok 4.7
- Released
- Sep 21, 2026
- Knowledge cutoff
- Jun 1, 2026
- Parameters
- N/A
- Context window
- 500K
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 4.7 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGrok 4.7 | Released | LLMBoard68.43 | ParametersN/A | Context500K | Max outputN/A | Open weightsNo | LicenseProprietary |
Models similar to Grok 4.7
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 4 Heavy
xAI
XA
Grok 4.5
xAI
XA
Grok 4.6
xAI
XA
Grok 4
xAI
XA
Grok 3
xAI
XA
Grok 4 Fast
xAI
What is Grok 4.7?
Key information about Grok 4.7 and its available data.
7 is a large language model from xAI. It is intended for long-running agents, coding, knowledge work, and visual projects.
Data as of 2026-11-10.
FAQ
Common questions about Grok 4.7.
When was Grok 4.7 released?
Grok 4.7's default version was released on Sep 21, 2026.
How much does Grok 4.7 cost?
Grok 4.7's official API price is $2 per million input tokens and $6 per million output tokens via xAI. The lowest tracked third-party offer starts at $1.6 input and $4.8 output via Prime Inference.
Who created Grok 4.7?
Grok 4.7 was created by xAI.
What is the context window for Grok 4.7?
The default version has a 500K token context window.
Is Grok 4.7 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 4.7?
27 provider offerings are linked to the default version.