xAI model product
Grok 4 Heavy is xAI’s multi-agent version of Grok 4, using multiple Grok 4 agents that work in parallel and collaborate on solutions.
Updated Sep 8, 2026. Default version: Grok-4 Heavy
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Grok-4 Heavy.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkHMMT25 | Score96.70% | Rank01 | Participants28 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkUSAMO25 | Score61.90% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score100.00% | Rank04 | Participants119 | Percentile97.46% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score79.40% | Rank13 | Participants75 | Percentile83.78% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score50.70% | Rank23 | Participants103 | Percentile78.43% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score88.40% | Rank35 | Participants247 | Percentile86.18% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
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.
Provider-specific output speed and catalog latency for Grok-4 Heavy. Runtime does not affect the capability score.
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.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGrok-4 Heavy | ReleasedN/A | LLMBoard67.18 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Grok 4 Heavy and its available data.
Grok 4 Heavy is an AI model from xAI that runs multiple Grok 4 agents in parallel, compares their solutions, and combines their insights. It uses approximately 10x more test-time compute than regular Grok 4 and scored over 50% on text-only problems from the Humanities Last Exam and a perfect result on AIME 2025.
Data as of 2026-09-08.
Common questions about Grok 4 Heavy.
A release date is not available for the default version.
No official standard PAYG price is currently available for Grok 4 Heavy.
Grok 4 Heavy was created by xAI.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.