#24Meta· released 2026-08-09

Meta: Muse Glimmer 30B.

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

View on OpenRouter ↗
Context
131K
Input $/1M
$0.30
Output $/1M
$1.10
Modality
text · image
Arena Elo
1442
LMArena — human blind votes
AA Index
63.0
Artificial Analysis composite
LiveBench
72.8
Contamination-resistant
GPQA
80.5%
Grad-level science reasoning
MMLU-Pro
81.9%
Broad knowledge
SWE-bench
64.6%
Real GitHub bugs (Verified)
Terminal-Bench
49.4%
Agentic shell tasks
ARC-AGI
15.2%
Abstract reasoning
Aider Polyglot
74.6%
Multi-language code editing
Speed
103 tok/s
Median output speed

Profile

Meta: Muse Glimmer 30B is Meta's entry at position #24 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard