xAI model product
Grok 4
Grok 4 is an xAI large language model for complex reasoning, mathematical problem-solving, and coding tasks.
Updated Sep 8, 2026. Default version: Grok-4
LLMBoard Score55.2Grok-4
Coverage40%7 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
Grok 4 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 4 Benchmark Results
Benchmark scores for Grok-4.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkUSAMO25 | Score37.50% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHMMT25 | Score90.00% | Rank06 | Participants28 | Percentile81.48% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score15.90% | Rank15 | Participants18 | Percentile17.65% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score79.00% | Rank15 | Participants75 | Percentile81.08% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search | Score1,141.52 rating | Rank24 | Participants28 | Percentile14.81% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,131.91 rating | Rank26 | Participants28 | Percentile7.41% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,121.48 rating | Rank28 | Participants28 | Percentile0.00% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score40.00% | Rank39 | Participants103 | Percentile62.75% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score91.70% | Rank41 | Participants119 | Percentile66.10% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score87.50% | Rank46 | Participants247 | Percentile81.71% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,210.06 rating | Rank59 | Participants107 | Percentile45.28% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,183.60 rating | Rank71 | Participants107 | Percentile33.96% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,418.96 rating | Rank89 | Participants121 | Percentile26.67% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,411.41 rating | Rank92 | Participants210 | Percentile56.46% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,410.98 rating | Rank100 | Participants210 | Percentile52.63% | EvidenceA | Evaluated |
Grok 4 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryentity recognition | Rank06 | Rating / score1,290.18 | Votes331 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing | Rank08 | Rating / score1,265.34 | Votes1,461 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank09 | Rating / score1,239.18 | Votes331 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank10 | Rating / score1,236.82 | Votes1,461 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank12 | Rating / score1,245.66 | Votes355 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank22 | Rating / score1,169.13 | Votes355 | ObservationsN/A | Result date |
| Arenasearch | Categoryoverall | Rank24 | Rating / score1,141.52 | Votes19,108 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank26 | Rating / score1,131.91 | Votes3,112 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank28 | Rating / score1,121.48 | Votes19,108 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank46 | Rating / score1,231.75 | Votes1,225 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank51 | Rating / score1,204.18 | Votes1,225 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank52 | Rating / score1,247.23 | Votes1,683 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank52 | Rating / score1,208.45 | Votes1,134 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank55 | Rating / score1,428.43 | Votes897 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank55 | Rating / score1,397.34 | Votes904 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank58 | Rating / score1,429.26 | Votes2,730 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank58 | Rating / score1,394.36 | Votes904 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank58 | Rating / score1,221.58 | Votes13,999 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank58 | Rating / score1,174.24 | Votes1,134 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank59 | Rating / score1,210.06 | Votes30,195 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank60 | Rating / score1,209.59 | Votes1,683 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank64 | Rating / score1,462.46 | Votes324 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank64 | Rating / score1,202.87 | Votes2,433 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank66 | Rating / score1,194.90 | Votes9,598 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank67 | Rating / score1,375.14 | Votes783 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank69 | Rating / score1,190.94 | Votes2,433 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank70 | Rating / score1,411.70 | Votes1,436 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank70 | Rating / score1,171.03 | Votes1,072 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank70 | Rating / score1,190.90 | Votes13,999 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank70 | Rating / score1,171.02 | Votes1,072 | ObservationsN/A | Result date |
Grok 4 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $3 input, $15 output per 1M via FastRouter
- Tracked offerings
- 6
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderFastRouter | Provider model IDx-ai/grok-4 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context256K | Updated |
| ProviderZenMux | Provider model IDx-ai/grok-4 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context256K | Updated |
| ProviderHelicone | Provider model IDgrok-4 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context256K | Updated |
| ProviderPoe | Provider model IDxai/grok-4 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context256K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgrok-4 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context256K | Updated |
| ProviderAbacus | Provider model IDgrok-4-0709 | Regionglobal | Input / 1M$3 | Output / 1M$15 | Context256K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Grok 4 Runtime Performance
Provider-specific output speed and catalog latency for Grok-4. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderxAI | Output Speed100.00 tok/s | Catalog Latency0.70 s | Max Input256K | Max Output8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 4 Specifications
Technical details for the model's default version.
- Version
- Grok-4
- Released
- Jul 9, 2025
- Knowledge cutoff
- Dec 31, 2024
- Parameters
- N/A
- Context window
- 256K
- Max output
- 8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 4 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 | Released | LLMBoard55.21 | ParametersN/A | Context256K | Max output8K | Open weightsNo | LicenseProprietary |
Models similar to Grok 4
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 4.20 Beta Reasoning
xAI
XA
Grok 3
xAI
XA
Grok 4 Fast
xAI
XA
Grok 4.1 Thinking
xAI
XA
Grok 3 Mini
xAI
XA
Grok 4.1
xAI
What is Grok 4?
Key information about Grok 4 and its available data.
Grok 4 is an xAI large language model announced in summer 2025 and built on version 6 of xAI's foundation model. It was trained using 200,000 GPUs and has acknowledged weaknesses in multimodal capabilities.
Data as of 2026-09-08.
FAQ
Common questions about Grok 4.
When was Grok 4 released?
Grok 4's default version was released on Jul 9, 2025.
How much does Grok 4 cost?
No official standard PAYG price is currently available for Grok 4. The lowest tracked third-party offer starts at $3 input and $15 output via FastRouter.
Who created Grok 4?
Grok 4 was created by xAI.
What is the context window for Grok 4?
The default version has a 256K token context window.
Is Grok 4 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 4?
6 provider offerings are linked to the default version.