xAI model product
Grok 2
Grok 2 is an LLM from xAI for chat, coding, reasoning, visual math reasoning, and document-based question answering.
Updated Sep 8, 2026. Default version: Grok-2
LLMBoard Score18.4Grok-2
Coverage0%8 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Grok 2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 2 Benchmark Results
Benchmark scores for Grok-2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkDocVQA | Score93.60% | Rank09 | Participants28 | Percentile70.37% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score69.00% | Rank16 | Participants39 | Percentile60.53% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score88.40% | Rank21 | Participants66 | Percentile69.23% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score87.50% | Rank24 | Participants101 | Percentile77.00% | EvidenceC | Evaluated |
| BenchmarkMATH | Score76.10% | Rank26 | Participants71 | Percentile64.29% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score66.10% | Rank38 | Participants64 | Percentile41.27% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score75.50% | Rank77 | Participants138 | Percentile44.53% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,335.44 rating | Rank159 | Participants210 | Percentile24.40% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,304.35 rating | Rank160 | Participants210 | Percentile23.92% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score56.00% | Rank178 | Participants247 | Percentile28.05% | EvidenceC | Evaluated |
Grok 2 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryjapanese | Rank130 | Rating / score1,270.15 | Votes1,478 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank131 | Rating / score1,244.19 | Votes1,478 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank131 | Rating / score1,278.82 | Votes952 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank134 | Rating / score1,236.53 | Votes952 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank137 | Rating / score1,313.85 | Votes1,609 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank138 | Rating / score1,317.32 | Votes604 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank138 | Rating / score1,286.59 | Votes1,609 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank138 | Rating / score1,351.78 | Votes604 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank142 | Rating / score1,316.84 | Votes9,339 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank145 | Rating / score1,314.28 | Votes10,293 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank145 | Rating / score1,365.48 | Votes3,813 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank145 | Rating / score1,326.71 | Votes17,406 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank147 | Rating / score1,280.39 | Votes671 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank149 | Rating / score1,355.97 | Votes3,206 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank150 | Rating / score1,311.82 | Votes671 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank152 | Rating / score1,281.95 | Votes10,293 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank153 | Rating / score1,325.76 | Votes3,813 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank153 | Rating / score1,318.83 | Votes29,136 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank154 | Rating / score1,326.26 | Votes8,745 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank155 | Rating / score1,342.17 | Votes5,317 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank156 | Rating / score1,289.24 | Votes5,317 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank156 | Rating / score1,305.94 | Votes3,206 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank158 | Rating / score1,291.53 | Votes17,406 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank158 | Rating / score1,351.38 | Votes10,796 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank158 | Rating / score1,335.29 | Votes8,902 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank159 | Rating / score1,284.10 | Votes9,339 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank159 | Rating / score1,287.76 | Votes40,763 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank159 | Rating / score1,335.44 | Votes63,498 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank160 | Rating / score1,314.41 | Votes10,796 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank160 | Rating / score1,283.70 | Votes7,604 | ObservationsN/A | Result date |
Grok 2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Grok 2 Runtime Performance
Provider-specific output speed and catalog latency for Grok-2. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderxAI | Output Speed85.00 tok/s | Catalog Latency0.70 s | Max Input128K | Max Output8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 2 Specifications
Technical details for the model's default version.
- Version
- Grok-2
- Released
- Aug 13, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 128K
- Max output
- 8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 2 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-2 | Released | LLMBoard18.43 | ParametersN/A | Context128K | Max output8K | Open weightsNo | LicenseProprietary |
Models similar to Grok 2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 2 mini
xAI
XA
Grok Code Fast 1
xAI
XA
Grok 1.5
xAI
XA
Grok 1.5V
xAI
XA
Grok 4.3
xAI
XA
Grok 4.1
xAI
What is Grok 2?
Key information about Grok 2 and its available data.
Grok 2 is a language model developed by xAI. It is described as supporting chat, coding, reasoning, visual math reasoning, document-based question answering, and academic benchmarks in reasoning, reading comprehension, math, and science.
Data as of 2026-09-08.
FAQ
Common questions about Grok 2.
When was Grok 2 released?
Grok 2's default version was released on Aug 13, 2024.
How much does Grok 2 cost?
No official standard PAYG price is currently available for Grok 2.
Who created Grok 2?
Grok 2 was created by xAI.
What is the context window for Grok 2?
The default version has a 128K token context window.
Is Grok 2 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 2?
No provider offering is currently linked to the default version.