Roboflow

Grok 4.6 vs Grok 4.7

Compare Grok 4.6 and Grok 4.7 side-by-side.

Compare Grok 4.6 vs Grok 4.7 live

Run the same image across every model that supports a task and compare their outputs side-by-side.

These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.

Models in this comparison

Grok 4.6 vs Grok 4.7 on Vision Evals

Grok 4.7 scores higher on 4 of the six Vision Evals tasks.

The widest gap is Object Detection, where Grok 4.7 leads 40.4% to 23.8%.

Overall, Grok 4.6 averages 68.7% (#28 of 54) against 71.9% (#22 of 54) for Grok 4.7.

Grok 4.6 is both cheaper ($0.0097 vs $0.012 per sample) and faster (17.5s vs 23.6s per sample).

Grok 4.6Grok 4.7

Grok 4.6 vs Grok 4.7 Comparison Table

Evals updated September 22, 2026Pricing updated September 22, 2026

PropertyGrok 4.6Grok 4.7
OrganizationSpaceXAISpaceXAI
Categoryclosedclosed
Modalitymultimodal
Release DateAug 2026Sep 2026
Context Window500K500K
Parameters
LicenseProprietaryProprietary
Pricing per 1M tokens
Input $/1M$2.00$1.60
Output $/1M$6.00$4.80
Vision Tasks
CaptioningDemo
Chart Question Answering
ClassificationDemo
Document Question Answering
Image Tagging
Multi-Label Classification
Object DetectionDemo
OCRDemo
Vision Language
Visual Question AnsweringDemo
Model Features
Foundation Vision
LLMs with Vision Capabilities
Multimodal Vision
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort
Overall
68.7%
71.9%
Avg cost / sample$0.0097$0.012
Avg speed / sample17.55s23.55s
By task
Object Detection (low)
23.8%
±2.8, Mean of 3 runs, range 20.2 to 25.9
$0.013
40.4%
±0.6, Mean of 3 runs, range 39.8 to 41.0
$0.017
Object Detection (high)
24.0%
±1.0, Mean of 3 runs, range 23.1 to 25.1
$0.041
41.2%
±1.6, Mean of 3 runs, range 39.6 to 42.8
$0.023
Counting (low)
65.8%
±4.1, Mean of 3 runs, range 62.2 to 70.3
$0.0079
61.7%
±1.3, Mean of 3 runs, range 60.8 to 63.5
$0.0086
Counting (high)
56.8%
±1.4, Mean of 3 runs, range 55.4 to 58.1
$0.027
60.8%
±1.3, Mean of 3 runs, range 59.5 to 62.2
$0.013
Identification (low)
84.4%
±3.1, Mean of 3 runs, range 81.3 to 87.5
$0.0055
87.5%
±3.1, Mean of 3 runs, range 84.4 to 90.6
$0.0050
Identification (high)
85.4%
±1.6, Mean of 3 runs, range 84.4 to 87.5
$0.015
80.2%
±1.6, Mean of 3 runs, range 78.1 to 81.3
$0.0074
OCR (low)
91.8%
±0.3, Mean of 3 runs, range 91.5 to 92.1
$0.0091
92.6%
±0.7, Mean of 3 runs, range 92.1 to 93.4
$0.014
OCR (high)
91.6%
±0.2, Mean of 3 runs, range 91.4 to 91.7
$0.023
93.5%
±0.3, Mean of 3 runs, range 93.1 to 93.8
$0.034
Data Extraction (low)
85.6%
±1.0, Mean of 3 runs, range 84.5 to 86.6
$0.0050
84.9%
±2.6, Mean of 3 runs, range 82.5 to 87.6
$0.0048
Data Extraction (high)
85.6%
±1.0, Mean of 3 runs, range 84.5 to 86.6
$0.0090
87.6%
±1.5, Mean of 3 runs, range 86.6 to 89.7
$0.0054
Reasoning (low)
61.1%
±1.3, Mean of 3 runs, range 59.6 to 62.3
$0.0093
64.2%
±2.3, Mean of 3 runs, range 62.3 to 66.9
$0.012
Reasoning (high)
63.8%
±2.0, Mean of 3 runs, range 62.3 to 66.2
$0.032
66.9%
±1.3, Mean of 3 runs, range 65.6 to 68.2
$0.019

Grok 4.6 vs Grok 4.7: Overview

Grok 4.6

Grok 4.6 is a proprietary reasoning model from xAI aimed at long-running agentic workflows, coding, and knowledge work. It accepts text and image input and returns text, with a 500,000 token context window and a knowledge cutoff of February 1, 2026. The model exposes an adjustable reasoning budget with low, medium, high, and xhigh settings, where high is the default, and it supports function calling, structured outputs, web and X search, and code execution as documented tool behaviors. Its visual capability covers interpreting images supplied alongside text prompts, which places it in the visual question answering and document understanding family, and it can also return object detection boxes as text coordinates when prompted.

xAI characterizes Grok 4.6 as the result of an extended post-training run over the Grok 4.5 lineage rather than a new pretrained base. The described recipe combines curated model-generated reasoning and technical data, engineering data, a revised optimizer, regenerated supervised fine-tuning trajectories, and reinforcement learning across agent environments spanning knowledge work, coding, kernel optimization, web development, and computer-aided design. Parameter count and architecture specifics are not disclosed. Independent measurement from Artificial Analysis places the model at 61 on its Intelligence Index, five points above Grok 4.5.

Grok 4.7

Grok 4.7 is a proprietary model from SpaceXAI, released on September 21, 2026. It accepts text and images as input and returns text. It extends Grok 4.6 and is listed at the same API price.

Its Vision Evals scores are on the leaderboard. Running it in the Playground is not available yet, because the inference workflow is not ready.

Frequently Asked Questions

On Roboflow's Vision Evals, Grok 4.7 performed better. It scores higher on 4 of the six vision tasks and averages 71.9% (#22 of 54) against 68.7% (#28 of 54) for Grok 4.6. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.

No. On the Vision Evals Object Detection benchmark at low effort, Grok 4.7 leads with 40.4% against 23.8%. This is the widest gap between the two models across the benchmark's tasks.

Grok 4.6 is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0097 per sample against $0.012. Grok 4.6 is priced at $2.00 per 1M input tokens and $6.00 per 1M output; Grok 4.7 is priced at $1.60 per 1M input tokens and $4.80 per 1M output. Actual costs depend on your image sizes, prompts, and output length.

Grok 4.6 is faster. Across Roboflow's Vision Evals it averaged 17.5s per inference against 23.6s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.