Meta AIopen-weight
Released: 2026-08-10Artificial AnalysisMuse Glimmer
Muse Glimmer from Meta, tracked on the Artificial Analysis Intelligence Index.
Intelligence Index
6.3/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
84tok/sec
Output streaming throughputTime to First Answer
27s
Time to first answer token, including any thinkingCost to Run the Index
0.18USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Muse Glimmer (High configuration). Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- 6.3
- Cost to run the Index
- $0.18
- Time per task
- 5.2 min
- Omniscience index
- -32.2
- Reasoning model
- Yes
- Cached-input price
- $0.04 / 1M
Reasoning & knowledge
- AA-Omniscience Accuracy28.0%
- CritPt2.6%
- CritPt v2 (Hard)7.0%
- GPQA Diamond83.5%
- HLE-Diamond9.1%
- Humanity's Last Exam22.0%
Coding & terminal agents
- FrontierCode 1.113.9%
- FrontierCode-AA 2.01.5%
- SciCode44.9%
- Terminal-Bench 2.151.7%
- Terminal-Bench 4.00.5%
- Terminal-Bench-Science 0.10.0%
Agentic work
- AA-AnalystAgent20.0%
- AA-Briefcase v1.1 (Elo)478 Elo
- AutomationBench-AA6.8%
- EnterpriseOps-Gym-AA34.7%
- GDPval-AA (normalized Elo)792 Elo
- τ³-Banking23.5%
Long context & documents
- AA-LCR (long-context reasoning)83.3%
- GDP.pdf10.0%
Multimodal & science
- MMMU-Pro74.3%
Health & safety
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Reasoning · CritPt v2 (Hard)7.0%
Coding & agents · Terminal-Bench 4.00.5%
Long context · AA-LCR83.3%
Knowledge · Humanity's Last Exam22.0%
Sourced Benchmark Evaluations (20)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| CritPt | Active | 2.6% | 93 | 2026-11-15 | independent | Source ↗ |
| EnterpriseOps-Gym-AA | Active | 34.7% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-AnalystAgent | Active | 20% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 6.8% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 10% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 1.5% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 16.4% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 28% | 93 | 2026-11-15 | independent | Source ↗ |
| HLE-Diamond | Active | 9.1% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 7% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode | Active | 13.9% | 98 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 83.3% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 0.5% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 51.7% | 93 | 2026-11-15 | independent | Source ↗ |
| τ³-Banking | Active | 23.5% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 44.9% | 93 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 74.3% | 93 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 22% | 93 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 83.5% | 78 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run meta-muse-glimmer
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "meta-muse-glimmer",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Muse Glimmer represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.