# Muse Glimmer

Muse Glimmer is an AI model released by Meta on Aug 10 2026. It has 30B parameters and open weight. At release it scored 83.5% on GPQA Diamond, 76% on SWE-Bench Verified and 51.2% on SWE-Bench Pro.

## Facts

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

## Benchmark scores published at release

| Benchmark | Score | What it measures |
| --- | --- | --- |
| SWE-Bench Pro | 51.2% | 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% | 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% | 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% | Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. |
| Humanity's Last Exam (no tools) | 22% | Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. |
| GPQA Diamond | 83.5% | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| OSWorld-Verified | 65.9% | 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 | economically valuable knowledge work (v2, re-based Elo) |
| CharXiv Reasoning | 78.8% | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 74% | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |

## About Muse Glimmer

Muse Glimmer, released August 10, 2026, was the first open model from Meta Superintelligence Labs and the end of the closed stretch that began with Muse Spark in April: a 30B dense model distilled from Muse Spark 1.2, published on Hugging Face under Apache 2.0. Meta pitched it at always-on local agents rather than raw capability — small enough to run on a single consumer GPU or a Mac, multimodal through a dedicated perception encoder, trained on more than 100 languages, and tuned for the parts of agent work that break in practice: tool calls with exact schemas, plans held over long horizons, and recovery after a tool returns something unexpected. The engineering around it aimed at the same target, with 4-bit quantization bringing memory under 20GB and DFlash speculative decoding cutting generation time by 3.1x on an RTX 5090 and 1.8x on an M5 Max.

Meta benchmarked it against the open models in its size class, Gemma 4 31B and Qwen3.6 27B, and led on agentic tool use: 75.5% on MCP Atlas at release against 54.2% and 62.5% for the other two, plus 74.6% on DeepSearch QA and 47.6% on WildClawBench. It scored 76.0% on SWE-Bench Verified, 51.2% on SWE-Bench Pro, 83.5% on GPQA Diamond, and 94.7% on AIME 2026, while Qwen3.6 took the computer-use and long-form coding rows — 75.6% to Muse Glimmer's 65.9% on OSWorld-Verified, 60.7% to 51.7% on Terminal-Bench 2.1. Unlike the Muse Spark 1.2 launch, Meta published a methodology report naming every harness and judge, though most of the comparison numbers were still its own reproductions rather than each model's self-reported best. Meta said open weights for a version of Muse Spark 1.2 would follow.

## 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 10 tracked benchmark scores — SWE-Bench Pro: 51.2%; SWE-Bench Verified: 76%; Terminal-Bench 2.1: 51.7%; MCP Atlas: 75.5%; Humanity's Last Exam (no tools): 22%; GPQA Diamond: 83.5%; OSWorld-Verified: 65.9%; GDPval-AA v2: 953; CharXiv Reasoning: 78.8%; MMMU-Pro: 74%. Scores are the figures published at release by Meta.

### 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 is the most recent Meta model tracked on AI Release Tracker.


---

Canonical page: https://aireleasetracker.com/model/meta/muse-glimmer
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.