xAI
grok-4
proprietaryMultimodal
Benchmark Average (0–100)
73.1%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
GPQA87.5%
Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.
AIME 202591.7%
AIME 2025 is a mathematics competition benchmark testing advanced problem-solving.
HLE40.0%
Humanity's Last Exam (HLE) is a multi-modal benchmark testing frontier knowledge across mathematics, humanities, and natural sciences with 2,500 expert-level questions.
OTHER BENCHMARKS
ARC-AGI v2
15.9%
MODEL INFO
Organization
xAI
Context Window
256,000
Release Date
2025-07-09
Knowledge Cutoff
2024-12-31
Parameters
—
License
proprietary
Input Price ($/M)
$3.0000
Output Price ($/M)
$15.0000
METADATA
Announcement Date
2025-07-09
Organization Country
US
Canonical ID
—