Data as of November 10, 2026 · How the score is built
Released Aug 10, 2026131K context
Muse Glimmer 30B
Decision readingMuse Glimmer 30B scores 32.4 out of 100 and ranks #171 of 214. This profile shows 14 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #61. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Released Aug 10, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
32.4/100
field median 51.1#171 of 214 ranked models
Public
#171of 214
Verified —
Price
Self-hosted; infrastructure cost varies
input median $0.60No comparable first-party hosted token rate
Speed
Not measured
field median 92 tok/sTime to first token not measured
Context
131Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Instruction Following ranks #61. A well-rounded choice across a range of tasks.
Validate before choosing
14 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 14 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #119 of 132Percentile 10thWeight 22%4 benchmarksVerified | 19.7 | 4 benchmarks | Verified | |||
| CodingRank #125 of 158Percentile 21stWeight 20%4 benchmarksVerified | 24.6 | 4 benchmarks | Verified | |||
| ReasoningRank #128 of 157Percentile 19thWeight 17%Not listedUnlisted sources | 28.1 | Not listed | Unlisted sources | |||
| MultimodalRank #62 of 67Percentile 8thWeight 12%4 benchmarksVerified | 41.7 | 4 benchmarks | Verified | |||
| KnowledgeRank #124 of 179Percentile 31stWeight 12%Not listedUnlisted sources | 37.6 | Not listed | Unlisted sources | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #61 of 157Percentile 62ndWeight 5%1 benchmarkVerified | 81.1 | 1 benchmark | Verified | |||
| MathRank Not rankedWeight 5%1 benchmarkVerified | 81.1 | 1 benchmark | Verified |
14 of 872 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic4/4 verified
- Coding4/4 verified
- ReasoningNot measured
- Multimodal4/4 verified
- KnowledgeNot measured
- MultilingualNot measured
- Inst. Following1/1 verified
- Math1/1 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Muse Glimmer 30B category percentile values
- Agentic10th percentile
- Coding21st percentile
- Reasoning19th percentile
- Multimodal8th percentile
- Knowledge31st percentile
- MultilingualNot eligible
- Instruction following62nd percentile
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#119/132
- Coding#125/158
- Reasoning#128/157
- Multimodal#62/67
- Knowledge#124/179
- MultilingualNot ranked
- Inst. Following#61/157
- MathNot ranked
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score51.2% | Versus best verified row Best verified: Claude Fable 5.2 · 93% | Gap41.8 behind | Weight26% ref. weight | Provider exact |
| SciCodeScientific Code Benchmark | Score43.6% | Versus best verified row Best verified: Sakana Fugu · 60.1% | Gap16.5 behind | Weight10% ref. weight | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score76% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap20 behind | WeightDisplay only | Provider exact |
| Terminal-Bench 2.1 | Score51.7% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap41.1 behind | WeightDisplay only | Provider exact |
Agentic4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| OSWorld-Verified | Score65.9% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap20.2 behind | Weight7% ref. weight | Provider exact |
| MCP Atlas | Score75.5% | Versus best verified row Best verified: Muse Spark Open · 89.2% | Gap13.7 behind | WeightDisplay only | Provider exact |
| DeepSearchQA | Score74.6% | Versus best verified row Best verified: Atria Dawn Preview · 96.0% | Gap21.4 behind | WeightDisplay only | Provider exact |
| skillsBench | Score44.3% | Versus best verified row Best verified: Qwen3.8 Max · 70.2% | Gap25.9 behind | WeightDisplay only | Provider exact |
Multimodal4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score74% | Versus best verified row Best verified: GPT-6.1 Terra · 85.5% | Gap11.5 behind | Weight30% ref. weight | Provider exact |
| CharXivCharXiv Reasoning | Score78.8% | Versus best verified row Best verified: Qwen3.8 Max · 93.5% | Gap14.7 behind | Weight17% ref. weight | Provider exact |
| ScreenSpot Pro | Score75.4% | Versus best verified row Best verified: GPT-6 Astra · 92.7% | Gap17.3 behind | WeightDisplay only | Provider exact |
| OmniDocBench 1.5 | Score75.8% | Versus best verified row Best verified: Qwen3.8 Max · 92.1% | Gap16.3 behind | WeightDisplay only | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | Score77% | Versus best verified row Best verified: Flint · 89.2% | Gap12.2 behind | WeightWeighted 70% | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME26AIME 2026 | Score94.7% | Versus best verified row Best verified: GLM-5.2 · 99.2% | Gap4.5 behind | WeightWeighted 25% | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 14 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
30b · 30B
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 131K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Meta publishes the full-precision and two 4-bit Muse Glimmer 30B checkpoints under Apache 2.0 on Hugging Face. The K-Quant-17GB release targets 24 GB hardware, while K-Quant-Dynamic targets 32 GB; Meta also ships a DFlash speculative-decoding drafter and a dedicated perception encoder.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Muse Glimmer 30B needs ~24GB VRAM (1× NVIDIA RTX 4090 (24GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Muse Glimmer 30B ranks #171 of 214 on the public leaderboard with a score of 32.41/100. It does not yet have enough sourced coverage for a verified position.
Muse Glimmer 30B is a open weight model with a 131K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Meta publishes the full-precision and two 4-bit Muse Glimmer 30B checkpoints under Apache 2.0 on Hugging Face. The K-Quant-17GB release targets 24 GB hardware, while K-Quant-Dynamic targets 32 GB; Meta also ships a DFlash speculative-decoding drafter and a dedicated perception encoder.
14 of 872 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #61, while its lowest eligible position is Reasoning at #128. a well-rounded choice across a range of tasks.
Last updated November 10, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Muse Glimmer 30B by API
3 hosts publish a per-token price for it. DeepInfra has the lowest output rate, $1.20 per million tokens. Prices read from each host’s own pages on October 20, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| DeepInfra | $0.30 | $1.20 | $0.04 | 131K |
| OpenRouter | $0.30 | $1.20 | $0.04 | 131K |
| Together AI | $0.35 | $1.50 | $0.04 | 131K |
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Ask your AI, from current BenchLM data
Where does Muse Glimmer 30B rank right now, and what does it cost?
Questions
How does Muse Glimmer 30B perform overall in AI benchmarks?
Muse Glimmer 30B ranks #171 out of 214 models on the public BenchAlign leaderboard, with a score of 32.41/100. Its evidence status is Estimated, and this profile shows 14 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Muse Glimmer 30B good for coding and programming?
Muse Glimmer 30B ranks #125 out of 158 eligible models for coding and programming, with a public category score of 24.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Muse Glimmer 30B good for mathematics?
Muse Glimmer 30B has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Muse Glimmer 30B good for agentic tool use and computer tasks?
Muse Glimmer 30B ranks #119 out of 132 eligible models for agentic tool use and computer tasks, with a public category score of 19.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Muse Glimmer 30B good for multimodal and grounded tasks?
Muse Glimmer 30B ranks #62 out of 67 eligible models for multimodal and grounded tasks, with a public category score of 41.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Muse Glimmer 30B good for instruction following?
Muse Glimmer 30B ranks #61 out of 157 eligible models for instruction following, with a public category score of 81.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Muse Glimmer 30B open source?
Muse Glimmer 30B is an open-weight model from Meta. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Muse Glimmer 30B have full benchmark coverage on BenchLM?
No. Muse Glimmer 30B currently has 29 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Muse Glimmer 30B?
Muse Glimmer 30B has a reported context window of 131K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.