Roboflow

Grok 4.6 vs Muse Glimmer 30B

Compare Grok 4.6 and Muse Glimmer 30B side-by-side. See how these vision models stack up in Image Captioning, Open Prompt, Classification, OCR, and Object Detection.

Compare Grok 4.6 vs Muse Glimmer 30B live

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

Detect and compare bounding boxes across models on the same image.

Open Object Detection in the full playground
GrokGrok 4.6
Run to compare this model.
MetaMuse Glimmer 30B
Run to compare this model.

Models in this comparison

Grok 4.6 vs Muse Glimmer 30B on Vision Evals

Muse Glimmer 30B scores higher on 4 of the six Vision Evals tasks.

The widest gap is Object Detection, where Muse Glimmer 30B leads 41.0% to 23.8%.

Overall, Grok 4.6 averages 68.7% (#33 of 61) against 70.8% (#29 of 61) for Muse Glimmer 30B.

Muse Glimmer 30B is both cheaper ($0.0011 vs $0.0097 per sample) and faster (8.7s vs 17.5s per sample).

Grok 4.6Muse Glimmer 30B

Grok 4.6 vs Muse Glimmer 30B Comparison Table

Evals updated September 29, 2026Pricing updated September 29, 2026

PropertyGrok 4.6Muse Glimmer 30B
OrganizationSpaceXAIMeta
Categoryclosedopen
Modalitymultimodalmultimodal
Release DateAug 2026Aug 2026
Context Window500K131K
Parameters29.6B
LicenseProprietaryApache 2.0
Pricing per 1M tokens
Input $/1M$2.00$0.300
Output $/1M$6.00$1.20
Vision Tasks
CaptioningDemoDemo
Chart Question Answering
ClassificationDemoDemo
Document Question Answering
Image Tagging
Multi-Label Classification
Object DetectionDemoDemo
OCRDemoDemo
Vision Language
Visual Question AnsweringDemoDemo
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%
70.8%
Avg cost / sample$0.0097$0.0011
Avg speed / sample17.55s8.70s
By task
Object Detection (low)
23.8%
±2.8, Mean of 3 runs, range 20.2 to 25.9
$0.013
41.0%
$0.0017
Object Detection (high)
24.0%
±1.0, Mean of 3 runs, range 23.1 to 25.1
$0.041
–
Counting (low)
65.8%
±4.1, Mean of 3 runs, range 62.2 to 70.3
$0.0079
66.2%
$0.0007
Counting (high)
56.8%
±1.4, Mean of 3 runs, range 55.4 to 58.1
$0.027
–
Identification (low)
84.4%
±3.1, Mean of 3 runs, range 81.3 to 87.5
$0.0055
81.3%
$0.0005
Identification (high)
85.4%
±1.6, Mean of 3 runs, range 84.4 to 87.5
$0.015
–
OCR (low)
91.8%
±0.3, Mean of 3 runs, range 91.5 to 92.1
$0.0091
92.1%
$0.0010
OCR (high)
91.6%
±0.2, Mean of 3 runs, range 91.4 to 91.7
$0.023
–
Data Extraction (low)
85.6%
±1.0, Mean of 3 runs, range 84.5 to 86.6
$0.0050
86.6%
$0.0006
Data Extraction (high)
85.6%
±1.0, Mean of 3 runs, range 84.5 to 86.6
$0.0090
–
Reasoning (low)
61.1%
±1.3, Mean of 3 runs, range 59.6 to 62.3
$0.0093
57.6%
$0.0009
Reasoning (high)
63.8%
±2.0, Mean of 3 runs, range 62.3 to 66.2
$0.032
62.9%
$0.0026

Grok 4.6 vs Muse Glimmer 30B: 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.

Muse Glimmer 30B

Muse Glimmer 30B is a dense vision language model from Meta built for long-horizon agentic work on local hardware. The architecture pairs a 52-layer causal text decoder with a roughly 1.8B parameter ViT-G/14 perception encoder for about 29.6 billion parameters in total, and it accepts interleaved text and image input so an agent can interpret screenshots, charts, and documents alongside conversation. The decoder uses grouped-query attention with 32 query heads and 2 key-value heads, a repeating pattern of three sliding-window local attention layers followed by one global layer, SwiGLU feed-forward blocks, and rotary position embeddings applied on the local layers, supporting a trained context of 131,072 tokens.

Meta describes the model as distilled from the larger Muse Spark and trained and evaluated around agentic behavior: end-to-end task completion, schema-accurate tool calling, multi-step reasoning across extended workflows, and recovery when a tool call returns an unexpected result. Reasoning effort is selectable across low, medium, high, and xhigh settings, and the model emits channel-scoped reasoning traces together with XML style tool calls rather than JSON, which requires parsers specific to this family. A companion block-diffusion drafter head predicts blocks of 16 tokens per forward pass for speculative decoding, with the main model verifying the proposals in parallel.

Frequently Asked Questions

On Roboflow's Vision Evals, Muse Glimmer 30B performed better. It scores higher on 4 of the six vision tasks and averages 70.8% (#29 of 61) against 68.7% (#33 of 61) 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, Muse Glimmer 30B leads with 41.0% against 23.8%. This is the widest gap between the two models across the benchmark's tasks.

Muse Glimmer 30B is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0011 per sample against $0.0097. Grok 4.6 is priced at $2.00 per 1M input tokens and $6.00 per 1M output; Muse Glimmer 30B is priced at $0.30 per 1M input tokens and $1.20 per 1M output. Actual costs depend on your image sizes, prompts, and output length.

Muse Glimmer 30B is faster. Across Roboflow's Vision Evals it averaged 8.7s per inference against 17.5s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.

Yes. The comparison demo on this page runs both models on the same image side by side for image captioning and open prompts in the free Roboflow Playground. You can try it instantly, and a free account unlocks unlimited runs.