Muse Spark 1.1 vs Qwen3.6 35B A3B
Muse Spark 1.1 leads Qwen3.6 35B A3B on the Artificial Analysis Intelligence Index, 33.7 to 18.2, and Qwen3.6 35B A3B costs 4.3x less per output token ($1.00 vs $4.25 per million). Updated October 23, 2026; 11 benchmarks have a result for both.
Muse Spark 1.1 or Qwen3.6 35B A3B: which to pick
Only Muse Spark 1.1 has a coding score, 70.3 on the Vibe Coding Index; Qwen3.6 35B A3B has none, so the two cannot be ranked on coding.
Pick Qwen3.6 35B A3B for output tokens 4.3x cheaper ($1.00 vs $4.25 per million).
- Shared results
- 11
- Muse Spark 1.1 only
- 93
- Qwen3.6 35B A3B only
- 9
- Like-for-like categories
- 5 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
No call
Only Muse Spark 1.1 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Muse Spark 1.1
Muse Spark 1.1 leads, 33.7 against 18.2.
Same board, both measured
Agentic work
AA Agentic Index
Muse Spark 1.1
Muse Spark 1.1 leads, 25.8 against 13.1.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Muse Spark 1.1 has a GPQA Diamond result, 91.2%.
Directional only
Knowledge
MMLU Pro
No call
Only Muse Spark 1.1 has a MMLU Pro result, 88.7%.
Directional only
Web design
Design Arena: websites
No call
Only Muse Spark 1.1 has a Design Arena: websites result, 1270.
Directional only
Long documents
Listed context window
Muse Spark 1.1
Muse Spark 1.1 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.6 35B A3B
Muse Spark 1.1 $0.0034, Qwen3.6 35B A3B $0.0006 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Muse Spark 1.1 has the number, $0.43.
Directional only
At a glance
- Coding index
- Muse Spark 1.1 70.3 from 3 benchmarks, Qwen3.6 35B A3B not benchmarked.
- Widest category
- Coding, 25.8 points apart on average over 2 shared benchmarks.
- Widest single gap
- AA Coding Index: Muse Spark 1.1 71.3 against Qwen3.6 35B A3B 41.9, 29.4 points apart on a 0 to 100 scale.
- Output price
- Muse Spark 1.1 $4.25 against Qwen3.6 35B A3B $1.00 per million output tokens, 4.3x apart.
- Context window
- Muse Spark 1.1 takes 1.05M tokens, Qwen3.6 35B A3B 262K.
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 | Muse Spark 1.1 | Bars | Qwen3.6 35B A3B | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| General | 4 | 0 | ||
| All shared boards | 11 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| LMArena WebDev | 1543 | Not measured | Only Muse Spark 1.1 measured |
| AA Coding Index | 71.3 | 41.9 | Muse Spark 1.1 |
| LiveCodeBench (Vals AI) | 85.9% | Not measured | Only Muse Spark 1.1 measured |
| SWE-bench Verified (Vals AI) | 82.0% | Not measured | Only Muse Spark 1.1 measured |
| Vibe Code Bench (Vals AI) | 72.2% | Not measured | Only Muse Spark 1.1 measured |
| Code migration (Vals AI) | 31.1% | Not measured | Only Muse Spark 1.1 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Muse Spark 1.1 measured |
| Terminal-Bench 2.1 (Vals AI) | 69.3% | Not measured | Only Muse Spark 1.1 measured |
| SkillsBench (Vals AI) | 59.2% | Not measured | Only Muse Spark 1.1 measured |
| SciCode | 58.8% | 36.6% | Muse Spark 1.1 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.8% | Only Qwen3.6 35B A3B measured |
| Terminal-Bench | Not measured | 24.6% | Only Qwen3.6 35B A3B measured |
| WeirdML | Not measured | 34.5% | Only Qwen3.6 35B A3B measured |
| LMArena Text: coding | 1498 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: software and IT | 1498 | Not measured | Only Muse Spark 1.1 measured |
| LMArena WebDev: React | 1532 | Not measured | Only Muse Spark 1.1 measured |
| LMArena WebDev: HTML | 1539 | Not measured | Only Muse Spark 1.1 measured |
| LMArena WebDev: from an image | 1540 | Not measured | Only Muse Spark 1.1 measured |
| SWE Atlas: Codebase QnA | 42.2% | Not measured | Only Muse Spark 1.1 measured |
| SWE Atlas: Test Writing | 41.5% | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 18.2 | Muse Spark 1.1 |
| Epoch Capabilities Index | 154.1 | 143.7 | Muse Spark 1.1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| AA Agentic Index | 25.8 | 13.1 | Muse Spark 1.1 |
| Design Arena: agents building web apps | 1207 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building full-stack apps | 1199 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building mobile apps | 1173 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building Android apps | 1178 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building Godot games | 1103 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building games | 1183 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: HTML slides | 1108 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: PowerPoint slides | 1122 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: spreadsheets | 1013 | Not measured | Only Muse Spark 1.1 measured |
| Finance Agent (Vals AI) | 57.2% | Not measured | Only Muse Spark 1.1 measured |
| Legal Research Bench (Vals AI) | 38.0% | Not measured | Only Muse Spark 1.1 measured |
| Excel Modeling Benchmark (Vals AI) | 56.4% | Not measured | Only Muse Spark 1.1 measured |
| Time Horizon Index (Vals AI) | 1.7% | Not measured | Only Muse Spark 1.1 measured |
| τ²-Bench Telecom | Not measured | 95.3% | Only Qwen3.6 35B A3B measured |
| APEX-Agents | 31.8% | Not measured | Only Muse Spark 1.1 measured |
| Vending-Bench 2 | $6,520 | Not measured | Only Muse Spark 1.1 measured |
| MCP Atlas | 88.1% | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| GPQA Diamond | 91.2% | Not measured | Only Muse Spark 1.1 measured |
| MMMU Pro (Vals AI) | 86.6% | Not measured | Only Muse Spark 1.1 measured |
| GPQA Diamond (Artificial Analysis run) | 89.8% | 84.1% | Muse Spark 1.1 |
| Humanity's Last Exam (Artificial Analysis run) | 46.2% | 22.2% | Muse Spark 1.1 |
| GPQA Diamond (Epoch AI run) | Not measured | 84.8% | Only Qwen3.6 35B A3B measured |
| Chess puzzles | 34.0% | Not measured | Only Muse Spark 1.1 measured |
| Mystery game puzzles | Not measured | 22.0% | Only Qwen3.6 35B A3B measured |
| LMArena Text: hard prompts | 1485 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: expert | 1478 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: hard prompts in English | 1480 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: diagrams | 1305 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: homework | 1287 | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 86.7% | Only Qwen3.6 35B A3B measured |
| FrontierMath, tiers 1 to 3 | Not measured | 20.4% | Only Qwen3.6 35B A3B measured |
| ProofBench | 39.0% | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: math | 1481 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: mathematical work | 1485 | Not measured | Only Muse Spark 1.1 measured |
| MathArena | 42.5% | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| MMLU Pro | 88.7% | Not measured | Only Muse Spark 1.1 measured |
| LegalBench (Vals AI) | 85.0% | Not measured | Only Muse Spark 1.1 measured |
| CorpFin (Vals AI) | 71.3% | Not measured | Only Muse Spark 1.1 measured |
| TaxEval (Vals AI) | 79.7% | Not measured | Only Muse Spark 1.1 measured |
| MortgageTax (Vals AI) | 66.1% | Not measured | Only Muse Spark 1.1 measured |
| SimpleQA Verified | 57.8% | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: science | 1483 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: medicine and healthcare | 1480 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: legal and government | 1482 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: business and finance | 1470 | Not measured | Only Muse Spark 1.1 measured |
| PRBench Finance | 55.0% | Not measured | Only Muse Spark 1.1 measured |
| PRBench Legal | 57.0% | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| Design Arena: websites | 1270 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: UI components | 1286 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: game dev | 1269 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: data viz | 1267 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: 3D | 1259 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: all code categories | 1276 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: SVG | 1233 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: ASCII art | 1267 | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 61.3% | Not measured | Only Muse Spark 1.1 measured |
| SAGE (Vals AI) | 45.6% | Not measured | Only Muse Spark 1.1 measured |
| MedScribe (Vals AI) | 88.9% | Not measured | Only Muse Spark 1.1 measured |
| Vals Multimodal Index | 66.7% | Not measured | Only Muse Spark 1.1 measured |
| IFBench | Not measured | 64.4% | Only Qwen3.6 35B A3B measured |
| Long context reasoning (AA-LCR) | 77.7% | 71.7% | Muse Spark 1.1 |
| DTBench | 94.4% | 73.9% | Muse Spark 1.1 |
| LMCA | 49.9% | 29.7% | Muse Spark 1.1 |
| Surface Evolver Bench | 52.5% | 44.4% | Muse Spark 1.1 |
| LMArena Text | 1478 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: instruction following | 1456 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: creative writing | 1435 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision | 1293 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: English | 1478 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: non-English | 1471 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: Chinese | 1515 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: German | 1469 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: Japanese | 1450 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: Korean | 1457 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: French | 1494 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: Spanish | 1462 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: Russian | 1481 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: Polish | 1497 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: multi-turn | 1484 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: longer queries | 1461 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: writing and language | 1447 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: entertainment and media | 1437 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: English | 1292 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: Chinese | 1348 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: reading text | 1301 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: humor | 1288 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Vision: creative writing | 1253 | Not measured | Only Muse Spark 1.1 measured |
| LMArena Document | 1465 | Not measured | Only Muse Spark 1.1 measured |
| MultiChallenge | 75.3% | Not measured | Only Muse Spark 1.1 measured |
| EQ-Bench 4 | 1260 | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B | 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
Qwen3.6 35B A3B costs less
Repository review
50K input + 3K output tokens
Qwen3.6 35B A3B costs less
Agent loop
200K input + 10K output tokens
Qwen3.6 35B A3B 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 Spark 1.1 | Qwen3.6 35B A3B |
|---|---|---|
| Maker | Meta | Qwen |
| Weights | No public weights listed | Open weights |
| Released | July 16, 2026 | April 27, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $1.25 | $0.10 |
| Output $/Mtok | $4.25 | $1.00 |
| Coding index | 70.3 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.43 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Muse Spark 1.1 better than Qwen3.6 35B A3B for coding?
Only Muse Spark 1.1 has a coding score, 70.3 on the Vibe Coding Index; Qwen3.6 35B A3B has none, so the two cannot be ranked on coding. Pick Qwen3.6 35B A3B for output tokens 4.3x cheaper ($1.00 vs $4.25 per million).
Which is cheaper, Muse Spark 1.1 or Qwen3.6 35B A3B?
Muse Spark 1.1 costs $1.25 per million input tokens and $4.25 per million output tokens; Qwen3.6 35B A3B costs $0.10 and $1.00. Cost per solved task is known for Muse Spark 1.1 only.
Which has the bigger context window, Muse Spark 1.1 or Qwen3.6 35B A3B?
Muse Spark 1.1, with 1.05M tokens against 262K.
How many benchmarks is the Muse Spark 1.1 vs Qwen3.6 35B A3B comparison based on?
11 benchmarks have a result for both models as of October 23, 2026. Muse Spark 1.1's coding index rests on 3 independent benchmarks and Qwen3.6 35B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.