Muse Wonder vs Extract
Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- 71.9
- Overall
- No data
- Output $/M
- $20.00
- Coding
- No data
- Overall
- No data
- Output $/M
- No data
Muse Wonder or Extract: which to pick
Only Muse Wonder has a coding score, 71.9 on the Vibe Coding Index; Extract has none, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
No benchmark has tested both yet. Muse Wonder has results on LMArena WebDev, Terminal-Bench 4 (Vals AI) and Vibe Code Bench (Vals AI); Extract has none yet. Compare them on price and context instead.
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
No call
Only Muse Wonder has a coding score, so no call is made.
One side not measured
Web design
Design Arena: websites
No call
Only Muse Wonder has a Design Arena: websites result, 1362.
Directional only
General
Vals Index
No call
Only Muse Wonder has a Vals Index result, 64.9%.
Directional only
Long documents
Listed context window
Muse Wonder
Muse Wonder takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Extract
Muse Wonder $0.014, Extract $0.0000 per turn.
List prices
At a glance
- Coding index
- Muse Wonder 71.9 from 3 benchmarks, Extract not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Muse Wonder $20.00 against Extract Free per million output tokens.
- Context window
- Muse Wonder takes 1.05M tokens, Extract 1M.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index13 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| LMArena WebDev | 1652 | Not measured | Only Muse Wonder measured |
| Terminal-Bench 4 (Vals AI) | 49.5% | Not measured | Only Muse Wonder measured |
| Vibe Code Bench (Vals AI) | 83.1% | Not measured | Only Muse Wonder measured |
| Code migration (Vals AI) | 62.5% | Not measured | Only Muse Wonder measured |
| IOI (Vals AI) | 66.9% | Not measured | Only Muse Wonder measured |
| SWE-bench Multimodal (Vals AI) | 45.6% | Not measured | Only Muse Wonder measured |
| Vibe Code Bench 1-100 (Vals AI) | 26.6% | Not measured | Only Muse Wonder measured |
| CyberBench (Vals AI) | 80.4% | Not measured | Only Muse Wonder measured |
| SciCode | 60.3% | Not measured | Only Muse Wonder measured |
| LMArena Text: coding | 1522 | Not measured | Only Muse Wonder measured |
| LMArena Text: software and IT | 1515 | Not measured | Only Muse Wonder measured |
| LMArena WebDev: React | 1641 | Not measured | Only Muse Wonder measured |
| LMArena WebDev: HTML | 1694 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| Epoch Capabilities Index | 161.8 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| Design Arena: spreadsheets | 1227 | Not measured | Only Muse Wonder measured |
| Finance Agent (Vals AI) | 56.6% | Not measured | Only Muse Wonder measured |
| Tax Agent Bench (Vals AI) | 36.3% | Not measured | Only Muse Wonder measured |
| Legal Research Bench (Vals AI) | 50.5% | Not measured | Only Muse Wonder measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 23.8% | Not measured | Only Muse Wonder measured |
| Excel Modeling Benchmark (Vals AI) | 67.1% | Not measured | Only Muse Wonder measured |
| BioMysteryBench (Vals AI) | 67.0% | Not measured | Only Muse Wonder measured |
| Terminal-Bench-Science (Vals AI) | 22.9% | Not measured | Only Muse Wonder measured |
| Vals Science Index | 39.1% | Not measured | Only Muse Wonder measured |
| CUA-bench (Vals AI) | 7.2% | Not measured | Only Muse Wonder measured |
| Vending-Bench 2 | $9,432 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | 27.5% | Not measured | Only Muse Wonder measured |
| Humanity's Last Exam (Artificial Analysis run) | 50.1% | Not measured | Only Muse Wonder measured |
| LMArena Text: hard prompts | 1506 | Not measured | Only Muse Wonder measured |
| LMArena Text: expert | 1513 | Not measured | Only Muse Wonder measured |
| LMArena Text: hard prompts in English | 1506 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| ProofBench | 84.0% | Not measured | Only Muse Wonder measured |
| LMArena Text: math | 1486 | Not measured | Only Muse Wonder measured |
| LMArena Text: mathematical work | 1514 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| LMArena Text: science | 1506 | Not measured | Only Muse Wonder measured |
| LMArena Text: medicine and healthcare | 1512 | Not measured | Only Muse Wonder measured |
| LMArena Text: legal and government | 1505 | Not measured | Only Muse Wonder measured |
| LMArena Text: business and finance | 1483 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| Design Arena: websites | 1362 | Not measured | Only Muse Wonder measured |
| Design Arena: UI components | 1374 | Not measured | Only Muse Wonder measured |
| Design Arena: game dev | 1377 | Not measured | Only Muse Wonder measured |
| Design Arena: data viz | 1321 | Not measured | Only Muse Wonder measured |
| Design Arena: 3D | 1426 | Not measured | Only Muse Wonder measured |
| Design Arena: all code categories | 1371 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index17 boards measured
| Benchmark | Muse Wonder | Extract | Leader |
|---|---|---|---|
| Vals Index | 64.9% | Not measured | Only Muse Wonder measured |
| Public Benefits Bench (Vals AI) | 70.2% | Not measured | Only Muse Wonder measured |
| Long context reasoning (AA-LCR) | 80.7% | Not measured | Only Muse Wonder measured |
| DTBench | 95.2% | Not measured | Only Muse Wonder measured |
| LMCA | 56.8% | Not measured | Only Muse Wonder measured |
| LMArena Text | 1502 | Not measured | Only Muse Wonder measured |
| LMArena Text: instruction following | 1491 | Not measured | Only Muse Wonder measured |
| LMArena Text: creative writing | 1491 | Not measured | Only Muse Wonder measured |
| LMArena Text: English | 1507 | Not measured | Only Muse Wonder measured |
| LMArena Text: non-English | 1492 | Not measured | Only Muse Wonder measured |
| LMArena Text: Chinese | 1537 | Not measured | Only Muse Wonder measured |
| LMArena Text: French | 1523 | Not measured | Only Muse Wonder measured |
| LMArena Text: Russian | 1522 | Not measured | Only Muse Wonder measured |
| LMArena Text: multi-turn | 1510 | Not measured | Only Muse Wonder measured |
| LMArena Text: longer queries | 1493 | Not measured | Only Muse Wonder measured |
| LMArena Text: writing and language | 1496 | Not measured | Only Muse Wonder measured |
| LMArena Text: entertainment and media | 1482 | Not measured | Only Muse Wonder measured |
| Neither model has a result on the other 29 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
Extract costs less
Repository review
50K input + 3K output tokens
Extract costs less
Agent loop
200K input + 10K output tokens
Extract 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 | Meta Muse Wonder | ScaleDown Extract |
|---|---|---|
| Maker | Meta | Scaledown |
| Weights | No public weights listed | No public weights listed |
| Released | October 12, 2026 | October 13, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $4.00 | $0.04 |
| Output $/Mtok | $20.00 | Free |
| Coding index | 71.9 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Muse Wonder better than Extract for coding?
Only Muse Wonder has a coding score, 71.9 on the Vibe Coding Index; Extract has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, Muse Wonder or Extract?
Muse Wonder costs $4.00 per million input tokens and $20.00 per million output tokens; Extract costs $0.04 and Free. Cost per solved task is known for neither of them.
Which has the bigger context window, Muse Wonder or Extract?
Muse Wonder, with 1.05M tokens against 1M.
Has any benchmark tested both Muse Wonder and Extract?
No benchmark has tested both yet. Muse Wonder has results on LMArena WebDev, Terminal-Bench 4 (Vals AI) and Vibe Code Bench (Vals AI); Extract has none yet. Compare them on price and context instead. Data as of October 21, 2026.