Skip to content

xAI Proprietary Released Jul 9, 2025 Updated

Grok-4

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Vision #91 / 167

    323 / 1,000

    ToolsGuide Score· votes 300, tests 381

  • Price per 1M tokens

    No listed price

Summary

Grok-4 is xAI's model, released Jul 9, 2025. It's ranked in 1 category and does best at vision: #91 of 167, with a ToolsGuide Score of 323 against a median of 346.

It has published results on 7 tests.

Specifications

Creator
xAI
Licence
Proprietary
Released
Jul 9, 2025
Context window
–
Input price
–
Output price
–
Tests reported
7
Settings ranked
Grok 4 (0709)

Model comparison

Against the ten best vision models.

Vision score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where Grok-4 sits among the top 20 in each category.

Vision

#91 of 167 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full vision leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Vision

Grok 4 (0709) · hover a bar for its rank

Test results

Every test Grok-4 has a published result on, out of 100%, with its rank among the models that took it.

  • GPQA

    #50 / 256

    Graduate-level science questions written to be hard to look up.

    87.5%

    Self-reported

  • AIME 2025

    #42 / 123

    Competition maths problems from the 2025 American Invitational Mathematics Exam.

    91.7%

    Self-reported

  • Humanity's Last Exam

    #40 / 108

    Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

    40.0%

    Self-reported · In the text score· In the vision score

  • LiveCodeBench

    #16 / 76

    LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

    79.0%

    Self-reported

  • HMMT25

    #6 / 28

    Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds

    90.0%

    Self-reported

  • ARC-AGI v2

    #15 / 19

    ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks. It evaluates fluid intelligence via input-output grid pairs (1x1 to 30x30) using colored cells (0-9), requiring models to identify underlying transformation rules from demonstration examples and apply them to test cases. Designed to be easy for humans but challenging for AI, focusing on core cognitive abilities like spatial reasoning, pattern recognition, and compositional generalization.

    15.9%

    Self-reported · In the text score· In the vision score

  • USAMO25

    #3 / 3

    The 2025 United States of America Mathematical Olympiad (USAMO) benchmark consists of six challenging mathematical problems requiring rigorous proof-based reasoning. USAMO is the most prestigious high school mathematics competition in the United States, serving as the final round of the American Mathematics Competitions series. This benchmark evaluates models on mathematical problem-solving capabilities beyond simple numerical computation, focusing on formal mathematical reasoning and proof generation.

    37.5%

    Self-reported