Creator

xAI

Released

2025-07-10

Intelligence

33.3

Artificial Analysis Index

Coding

Artificial Analysis Index

In $/1M

$3.00

input tokens

Out $/1M

$15.00

output tokens

Blended $/1M

$6.00

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Proprietary

non-commercial

Weights

Closed

API only

Modalities

Image · Text

Parameters

Grok 4, announced by xAI in summer 2025, represents a major leap in AI capabilities, described as 'the smartest AI in the world.' Built on version 6 of xAI's foundation model, it uses 100x more training compute than Grok 2 and 10x more reinforcement learning compute than Grok 3. The model achieves PhD-level performance across all academic disciplines simultaneously, scoring perfect on standardized tests like the SAT and near-perfect on graduate exams like the GRE. Unlike Grok 3, tool usage is built into the training process rather than relying on generalization. Trained using 200,000 GPUs, Grok 4 excels at complex reasoning, mathematical problem-solving, and coding tasks, though it has acknowledged weaknesses in multimodal capabilities that are being addressed in the next version.

Capability profile

Category strength across 20 domains, via LLM Stats.

biology
90physics
90chemistry
90code
80math
60
general
60reasoning
60vision
30spatial reasoning
20
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
88
Humanity’s Last Exam
24
MMLU-Pro
87
SciCode
46
LiveCodeBench
82
MATH-500
99
AIME 2025
93
τ²-Bench (agentic)
75
Terminal-Bench Hard
38
IFBench
54
Via Artificial Analysis
© 2026 NYSGPT2525 LLC