Ember-1 vs Muse Ember
Muse Ember leads Ember-1 on coding, 64.9 to 52.6 on the Vibe Coding Index, and Muse Ember costs 30.0x less per output token ($0.50 vs $15.00 per million). Updated November 14, 2026; 4 benchmarks have a result for both.
Ember-1 or Muse Ember: which to pick
Pick Muse Ember for coding: it scores 64.9 on the Vibe Coding Index against 52.6 for Ember-1.
Pick Ember-1 for work measured by Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 4
- Ember-1 only
- 12
- Muse Ember only
- 11
- Like-for-like categories
- 2 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Muse Ember
Muse Ember scores 64.9 against 52.6.
2 and 3 benchmarks behind the scores
General
Vals Index
No call
Only Muse Ember has a Vals Index result, 60.5%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Muse Ember
Ember-1 $0.011, Muse Ember $0.0003 per turn.
List prices
At a glance
- Coding index
- Ember-1 52.6 from 2 benchmarks, Muse Ember 64.9 from 3 benchmarks.
- Widest category
- Coding, 12.5 points apart on average over 2 shared benchmarks.
- Widest single gap
- Terminal-Bench 4 (Vals AI): Ember-1 20.7% against Muse Ember 39.4%, 24.9 points apart on a 0 to 100 scale.
- Output price
- Ember-1 $15.00 against Muse Ember $0.50 per million output tokens, 30.0x apart.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Ember-1 | Bars | Muse Ember | Ties |
|---|---|---|---|---|
| Coding | 1 | 1 | ||
| Agentic work | 0 | 2 | ||
| All shared boards | 1 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index11
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1609 | Only Muse Ember measured |
| Terminal-Bench 4 (Vals AI) | 20.7% | 39.4% | Muse Ember |
| Vibe Code Bench (Vals AI) | 83.9% | 83.7% | Ember-1 |
| Code migration (Vals AI) | 32.5% | Not measured | Only Ember-1 measured |
| IOI (Vals AI) | 46.3% | Not measured | Only Ember-1 measured |
| CyberBench (Vals AI) | 69.5% | Not measured | Only Ember-1 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | Not measured | 40.9% | Only Muse Ember measured |
| FrontierCode 2.0 | Not measured | 27.2% | Only Muse Ember measured |
| LMArena WebDev: React | Not measured | 1616 | Only Muse Ember measured |
| LMArena WebDev: HTML | Not measured | 1621 | Only Muse Ember measured |
| GameBench 2 | 63.1 | Not measured | Only Ember-1 measured |
| Neither model has a result on the other 41 boards here | |||
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| Neither model has a result on 2 boards here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | 51.8% | Not measured | Only Ember-1 measured |
| Tax Agent Bench (Vals AI) | 31.1% | 38.2% | Muse Ember |
| Legal Research Bench (Vals AI) | 44.7% | 49.0% | Muse Ember |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 25.0% | Only Muse Ember measured |
| Excel Modeling Benchmark (Vals AI) | 63.4% | Not measured | Only Ember-1 measured |
| BioMysteryBench (Vals AI) | 67.0% | Not measured | Only Ember-1 measured |
| Terminal-Bench-Science (Vals AI) | 5.7% | Not measured | Only Ember-1 measured |
| Vals Science Index | 31.8% | Not measured | Only Ember-1 measured |
| APEX-Agents | Not measured | 64.3% | Only Muse Ember measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | 22.5% | Not measured | Only Ember-1 measured |
| HLE-Diamond (Artificial Analysis run) | Not measured | 25.1% | Only Muse Ember measured |
| CritPt v2, hard subset (Artificial Analysis run) | Not measured | 39.0% | Only Muse Ember measured |
| Neither model has a result on the other 23 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| Neither model has a result on 14 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| AA-Omniscience | Not measured | 7.7 | Only Muse Ember measured |
| Neither model has a result on the other 20 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| Vals Index | Not measured | 60.5% | Only Muse Ember measured |
| Public Benefits Bench (Vals AI) | 66.2% | Not measured | Only Ember-1 measured |
| SAGE (Vals AI) | 86.4% | Not measured | Only Ember-1 measured |
| Neither model has a result on the other 46 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Muse Ember | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Muse Ember costs less
Repository review
50K input + 3K output tokens
Muse Ember costs less
Agent loop
200K input + 10K output tokens
Muse Ember costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Fireworks Ember-1 | Meta Muse Ember |
|---|---|---|
| Maker | Fireworks | Meta |
| Weights | No public weights listed | No public weights listed |
| Released | September 24, 2026 | November 9, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $3.00 | $0.10 |
| Output $/Mtok | $15.00 | $0.50 |
| Coding index | 52.6 | 64.9 |
| Independent measurements behind it | 2 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Ember-1 better than Muse Ember for coding?
Pick Muse Ember for coding: it scores 64.9 on the Vibe Coding Index against 52.6 for Ember-1. Pick Ember-1 for work measured by Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, Ember-1 or Muse Ember?
Ember-1 costs $3.00 per million input tokens and $15.00 per million output tokens; Muse Ember costs $0.10 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Ember-1 or Muse Ember?
Neither: both take 1.05M tokens.
How many benchmarks is the Ember-1 vs Muse Ember comparison based on?
4 benchmarks have a result for both models as of November 14, 2026. Ember-1's coding index rests on 2 independent benchmarks and Muse Ember's on 3. Where only one model has a result, the page says so instead of naming a winner.