# Muse Glimmer

Muse Glimmer is an AI model released by Meta on Aug 10 2026. It has 30B parameters, a 128k context window and open weight. Tracked results include 22% on Humanity's Last Exam (text only, no tools), 83.5% on GPQA Diamond and 76% on SWE-Bench Verified.

## Facts

| Field | Value |
| --- | --- |
| Model | Muse Glimmer |
| Developer | Meta |
| Release date | Monday, Aug 10 2026 |
| Licensing | Open Weight |
| Parameters | 30B |
| Context window | 128k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| SWE-Bench Pro | 51.2% | Lab | Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. |
| SWE-Bench Verified | 76% | Lab | Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. |
| Terminal-Bench 2.1 | 51.7% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. |
| MCP Atlas | 75.5% | Lab | Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. |
| DeepSearchQA | 74.6% | Lab | Questions that cannot be answered from one page: the AI has to search the web, follow the trail across several sources, and put the pieces together into an answer. Higher is better. |
| Humanity's Last Exam (text only, no tools) | 22% | Lab | accuracy on the 2,158 text-only questions without tools |
| GPQA Diamond | 83.5% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| IFBench | 77% | Lab | Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. |
| OSWorld-Verified | 65.9% | Lab | Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. |
| GDPval-AA v2 | 953 | Lab | economically valuable knowledge work (v2, re-based Elo) |
| CharXiv Reasoning | 78.8% | Lab | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 74% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |

## About Muse Glimmer

Muse Glimmer was introduced on August 10, 2026 as Meta's 30-billion-parameter model for local agent workflows. Meta released the weights under Apache 2.0 and emphasized tool calling, local coding and running assistants on user-controlled hardware. The model's compact size was chosen around the memory and computation constraints of those deployments.

The release included a model card and deployment guidance, with optimized software integrations following separately. Local operation could keep model inference on the user's device, while any connected tools or external services still determined what information left it. Glimmer was a distinct deployment option from the hosted Muse Spark models. Muse Ember, announced on November 9, 2026, is a hosted API model for high-volume work and was not released as weights.

## Questions and answers

### When was Muse Glimmer released?

Muse Glimmer was released by Meta on Monday, Aug 10 2026.

### Who made Muse Glimmer?

Muse Glimmer was built by Meta. Develops the open-weight Llama series of models. Committed to open-source AI research.

### What benchmark scores did Muse Glimmer get?

Muse Glimmer reports 12 tracked benchmark scores — SWE-Bench Pro: 51.2%; SWE-Bench Verified: 76%; Terminal-Bench 2.1: 51.7%; MCP Atlas: 75.5%; DeepSearchQA: 74.6%; Humanity's Last Exam (text only, no tools): 22%; GPQA Diamond: 83.5%; IFBench: 77%; OSWorld-Verified: 65.9%; GDPval-AA v2: 953; CharXiv Reasoning: 78.8%; MMMU-Pro: 74%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. It holds the best score among all models tracked here on Humanity's Last Exam (text only, no tools).

### What is the context window of Muse Glimmer?

Muse Glimmer has a context window of 128k. Providers may specify separate input and output token limits.

### How many parameters does Muse Glimmer have?

Muse Glimmer is reported at 30B parameters.

### Is Muse Glimmer open source?

Partly. Muse Glimmer is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Muse Glimmer?

Meta's previous tracked release was Muse Spark 1.2 on Aug 5 2026, 5 days earlier. It was followed by Muse Spark 1.3 on Sep 2 2026.


---

Canonical page: https://aireleasetracker.com/model/meta/muse-glimmer
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.