xAI: Grok 3

xAI: Grok 3

x-ai · Released Jun 10, 2025 Professional
Intelligence #13 / 610
82.0 Our Score
Speed #273 / 286
31.0 tokens / sec
Input #544 / 610
$3.00 per 1M tokens
Output #551 / 610
$15.00 per 1M tokens
Context #260 / 610
131,072 tokens

Analysis Summary

Grok 3 is xAI's full-size model, with solid GPQA, MMLU Pro, and long-context reasoning scores. Tool use and function calling are supported across a 131K context window, and the instruction-following benchmark is among the stronger results in its tier. However, its intelligence index of 18.4 is lower than Grok 3 Mini's 22.5, which is an unusual inversion.

For businesses, Grok 3 suits general reasoning, content drafting, and code assistance tasks. The long-context reliability (lcr 0.547) is a genuine advantage for document-heavy workflows. That said, the text-only modality limits its versatility compared to multimodal alternatives at similar price points.

At $3.00 input and $15.00 output per million tokens, the cost is difficult to justify when Grok 3 Mini outperforms it on key benchmarks at a fraction of the price. Unless a specific use case demands the full model, Grok 3 Mini is the more rational choice for most business deployments.

Assessed July 10, 2026

Editorial notes

Grok 3 from xAI offers strong reasoning, coding, and long-context performance with tool use and function calling, but its $3/$15 pricing is hard to justify given Grok 3 Mini's superior benchmark scores at a fraction of the cost.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.4Technical3.6Value5.8Content5.8
Intelligence 3.4/10
Technical 3.6/10
Content 5.8/10
Value 5.8/10

How xAI: Grok 3 compares

XAI: Grok 3 ranks #158 of 392 AI models we track for overall intelligence, #151 of 296 for agentic tasks. Its 131K-token context window is larger than 57% of the models we list. At $3.00 per million input tokens it is cheaper than 11% of comparable models.

About xAI: Grok 3

Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

18.4 Intelligence Index
30.1 Agentic Index
58 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 69.3% Graduate-level scientific reasoning
HLE 5.1% Humanity's Last Exam
MMLU Pro 79.9% Multi-task language understanding
MATH 500 87% Mathematical problem-solving
AIME 33% Competition mathematics
AIME 2025 58% Competition mathematics (2025)
SciCode 36.8% Scientific computing

Technical

LiveCodeBench 42.5% Live coding evaluation
TerminalBench Hard 11.4% Agentic terminal tasks
τ²-Bench 48.8% Conversational agent benchmark

Content

IFBench 46.9% Instruction following
LCR 54.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does xAI: Grok 3 stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID x-ai/grok-3
Providerx-ai
Release Date June 10, 2025
Context Length131,072 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $3.00 $0.003000
Output $15.00 $0.015000

Leaderboard Categories

Frequently asked questions about xAI: Grok 3

How much does xAI: Grok 3 cost?

xAI: Grok 3 costs $3.00 per million input tokens and $15.00 per million output tokens.

What is the context window of xAI: Grok 3?

xAI: Grok 3 has a context window of 131,072 tokens (131K).

What can xAI: Grok 3 do?

xAI: Grok 3 supports tool use and function calling.

Who created xAI: Grok 3?

xAI: Grok 3 is developed by xAI and was released on June 10, 2025.