- Score
- 8.6 (-0.07 points)
- Total Cost (Current Price)
- $0.061 · 46.7% cheaper
- Response Time (avg)
- 7.51s · 8.7% faster
Meta
Release: 2026-11-09
Tested on: 2026-11-09 21:37
meta/muse-ember::low
~150B total (~10B active)MoEClosedEstimated
Muse Ember scores above Muse Wonder for under 5% of the cost →
Summary
Muse Ember scores 8.6 on AI BENCHY and ranks #86. It has 10.0 reliability, a 72.5% pass rate, $0.114 total cost, and 8.22s average response time.
What makes Muse Ember unique: Its total benchmark cost is unusually low for its score range.
Recommended alternatives
We recommend choosing this model instead:
Model facts
Researched on 2026-11-09
- Parameters
- ~150B total (~10B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Meta lists Muse Ember (muse-ember-1.0) as the smallest, efficient execution model among API-hosted Muse models, with no public weights and no disclosed size or architecture. The 150B total / 10B active MoE values are a low-confidence small-tier catalog estimate, scaled down from the Muse Spark family estimate and consistent with its $0.10/$0.50 price.
8.6
Consistency
8.9
10.0
$0.114
Total Output Tokens
169,226
Total Input Tokens
288,136
Input Price
$0.100 / 1M
Output Price
$0.500 / 1M
Cache Read Price
$0.004 / 1M
Cache Write Price
$0.125 / 1M
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#86 Muse Ember
low- Cost
- $0.003
- Time
- 11.3s
- Tokens
- 4,679 tok
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Muse EmberlowvsClaude Fable 5.2highMuse EmberlowvsMuse EmbermaxMuse EmberlowvsGPT-6 SollowMuse EmberlowvsDeepSeek V4.1 FlashmaxMuse EmberlowvsSeed 2.1 TurbomediumMuse EmberlowvsGPT-6.1 TerranoneMuse EmberlowvsMiMo-V2.6-PromediumMuse EmberlowvsMuse Spark 1.1lowMuse EmberlowvsQwen3.8 27BhighFree AvailableMuse EmberlowvsClaude Fable 5.2low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 10.0 | 10.0 | |
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 10.0 | 10.0 | |
| Combined | 7.3 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.5 | 4.4 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 6.5 | 10.0 | |
| Puzzle Solving | 5.3 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |