DeepSeek V4 Pro 0423 vs Muse Spark 1.1
Updated October 21, 2026. 70 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Muse Spark 1.1 for coding: it scores 48.9 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.
Pick DeepSeek V4 Pro 0423 when output tokens cost 2.2x less, or when what matters is LiveCodeBench (Vals AI) or AA Agentic Index, where it leads.
- Shared results
- 70
- DeepSeek V4 Pro 0423 only
- 13
- Muse Spark 1.1 only
- 26
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Muse Spark 1.1
Muse Spark 1.1 scores 48.9 against 35.3.
One benchmark behind each score
Intelligence
AA Intelligence Index
Muse Spark 1.1
Muse Spark 1.1 leads, 33.7 against 30.4.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 26.3 against 25.8.
Same board, both measured
Reasoning
GPQA Diamond
Muse Spark 1.1
Muse Spark 1.1 leads, 91.2% against 89.4%.
Same board, both measured
Knowledge
MMLU Pro
Muse Spark 1.1
Muse Spark 1.1 leads, 88.7% against 87.3%.
Same board, both measured
Web design
Design Arena: websites
Muse Spark 1.1
Muse Spark 1.1 leads, 1270 against 1235.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 $0.0019, Muse Spark 1.1 $0.0034 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Muse Spark 1.1
DeepSeek V4 Pro 0423 $0.57, Muse Spark 1.1 $0.43.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Pro 0423 35.3 from 1 benchmark, Muse Spark 1.1 48.9 from 1 benchmark.
- Widest category
- Agentic work, 14.5 points apart on average over 8 shared benchmarks.
- Widest single gap
- Design Arena: agents building full-stack apps: DeepSeek V4 Pro 0423 948 against Muse Spark 1.1 1199, 31.4 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0423 $1.9105 against Muse Spark 1.1 $4.25 per million output tokens, 2.2x 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 | DeepSeek V4 Pro 0423 | Bars | Muse Spark 1.1 | Ties |
|---|---|---|---|---|
| Coding | 1 | 11 | 1 tie | |
| Intelligence | 0 | 2 | ||
| Agentic work | 1 | 7 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 9 | ||
| Web design | 0 | 8 | ||
| General | 2 | 20 | ||
| All shared boards | 4 | 65 | 1 tie |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index111
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| LMArena WebDev | 1447 | 1542 | Muse Spark 1.1 |
| AA Coding Index | 59.4 | 71.3 | Muse Spark 1.1 |
| LiveCodeBench (Vals AI) | 87.5% | 85.9% | DeepSeek V4 Pro 0423 |
| SWE-bench Verified (Vals AI) | 77.4% | 82.0% | Muse Spark 1.1 |
| Terminal-Bench 4 (Vals AI) | 11.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Vibe Code Bench (Vals AI) | 49.9% | 72.2% | Muse Spark 1.1 |
| Code migration (Vals AI) | 26.2% | 31.1% | Muse Spark 1.1 |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | 69.3% | Muse Spark 1.1 |
| SkillsBench (Vals AI) | 51.3% | 59.2% | Muse Spark 1.1 |
| SciCode | Not measured | 58.8% | Only Muse Spark 1.1 measured |
| FrontierCode | 17.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| WeirdML | 48.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ALE-Bench | 1006.1 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: coding | 1470 | 1498 | Muse Spark 1.1 |
| LMArena Text: software and IT | 1469 | 1498 | Muse Spark 1.1 |
| LMArena WebDev: React | 1441 | 1532 | Muse Spark 1.1 |
| LMArena WebDev: HTML | 1435 | 1540 | Muse Spark 1.1 |
| LMArena WebDev: from an image | Not measured | 1540 | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 33.7 | Muse Spark 1.1 |
| Epoch Capabilities Index | 149.1 | 154.1 | Muse Spark 1.1 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | 25.8 | DeepSeek V4 Pro 0423 |
| Design Arena: agents building web apps | 1000 | 1207 | Muse Spark 1.1 |
| Design Arena: agents building full-stack apps | 948 | 1199 | Muse Spark 1.1 |
| Design Arena: agents building mobile apps | Not measured | 1177 | Only Muse Spark 1.1 measured |
| Design Arena: agents building Android apps | Not measured | 1184 | Only Muse Spark 1.1 measured |
| Design Arena: agents building Godot games | 1059 | 1103 | Muse Spark 1.1 |
| Design Arena: agents building games | Not measured | 1183 | Only Muse Spark 1.1 measured |
| Design Arena: HTML slides | Not measured | 1194 | Only Muse Spark 1.1 measured |
| Design Arena: PowerPoint slides | Not measured | 1156 | Only Muse Spark 1.1 measured |
| Design Arena: spreadsheets | Not measured | 974 | Only Muse Spark 1.1 measured |
| Finance Agent (Vals AI) | 44.1% | 57.2% | Muse Spark 1.1 |
| Tax Agent Bench (Vals AI) | 25.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Legal Research Bench (Vals AI) | 23.1% | 38.0% | Muse Spark 1.1 |
| Excel Modeling Benchmark (Vals AI) | 51.6% | 56.4% | Muse Spark 1.1 |
| Time Horizon Index (Vals AI) | Not measured | 1.7% | Only Muse Spark 1.1 measured |
| APEX-Agents | Not measured | 31.8% | Only Muse Spark 1.1 measured |
| Vending-Bench 2 | $3,285 | $6,520 | Muse Spark 1.1 |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| GPQA Diamond | 89.4% | 91.2% | Muse Spark 1.1 |
| MMMU Pro (Vals AI) | Not measured | 86.6% | Only Muse Spark 1.1 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.8% | Only Muse Spark 1.1 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 46.2% | Only Muse Spark 1.1 measured |
| GPQA Diamond (Epoch AI run) | 90.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Chess puzzles | 19.0% | 34.0% | Muse Spark 1.1 |
| Mystery game puzzles | 17.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: hard prompts | 1461 | 1485 | Muse Spark 1.1 |
| LMArena Text: expert | 1463 | 1478 | Muse Spark 1.1 |
| LMArena Text: hard prompts in English | 1466 | 1480 | Muse Spark 1.1 |
| LMArena Vision: diagrams | Not measured | 1305 | Only Muse Spark 1.1 measured |
| LMArena Vision: homework | Not measured | 1287 | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 96.7% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| FrontierMath, tiers 1 to 3 | 45.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ProofBench | 16.0% | 39.0% | Muse Spark 1.1 |
| LMArena Text: math | 1443 | 1482 | Muse Spark 1.1 |
| LMArena Text: mathematical work | 1455 | 1487 | Muse Spark 1.1 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 88.7% | Muse Spark 1.1 |
| LegalBench (Vals AI) | 80.3% | 85.0% | Muse Spark 1.1 |
| CaseLaw (Vals AI) | 59.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CorpFin (Vals AI) | 61.4% | 71.3% | Muse Spark 1.1 |
| TaxEval (Vals AI) | 72.1% | 79.7% | Muse Spark 1.1 |
| MortgageTax (Vals AI) | Not measured | 66.1% | Only Muse Spark 1.1 measured |
| MedCode (Vals AI) | 40.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SimpleQA Verified | 47.0% | 57.8% | Muse Spark 1.1 |
| LMArena Text: science | 1470 | 1484 | Muse Spark 1.1 |
| LMArena Text: medicine and healthcare | 1466 | 1479 | Muse Spark 1.1 |
| LMArena Text: legal and government | 1464 | 1481 | Muse Spark 1.1 |
| LMArena Text: business and finance | 1443 | 1470 | Muse Spark 1.1 |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1235 | 1270 | Muse Spark 1.1 |
| Design Arena: UI components | 1221 | 1290 | Muse Spark 1.1 |
| Design Arena: game dev | 1229 | 1269 | Muse Spark 1.1 |
| Design Arena: data viz | 1203 | 1268 | Muse Spark 1.1 |
| Design Arena: 3D | 1254 | 1260 | Muse Spark 1.1 |
| Design Arena: all code categories | 1240 | 1276 | Muse Spark 1.1 |
| Design Arena: SVG | 1139 | 1234 | Muse Spark 1.1 |
| Design Arena: ASCII art | 1148 | 1270 | Muse Spark 1.1 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index220
| Benchmark | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 62.9% | 61.3% | DeepSeek V4 Pro 0423 |
| SAGE (Vals AI) | Not measured | 45.6% | Only Muse Spark 1.1 measured |
| MedScribe (Vals AI) | 75.1% | 88.9% | Muse Spark 1.1 |
| Vals Multimodal Index | Not measured | 66.7% | Only Muse Spark 1.1 measured |
| Long context reasoning (AA-LCR) | Not measured | 77.7% | Only Muse Spark 1.1 measured |
| DTBench | 90.7% | 94.4% | Muse Spark 1.1 |
| LMCA | 41.2% | 49.9% | Muse Spark 1.1 |
| Surface Evolver Bench | 40.0% | 52.5% | Muse Spark 1.1 |
| CL-bench Life | 13.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1451 | 1478 | Muse Spark 1.1 |
| LMArena Text: instruction following | 1445 | 1457 | Muse Spark 1.1 |
| LMArena Text: creative writing | 1446 | 1435 | DeepSeek V4 Pro 0423 |
| LMArena Vision | Not measured | 1293 | Only Muse Spark 1.1 measured |
| LMArena Text: English | 1459 | 1478 | Muse Spark 1.1 |
| LMArena Text: non-English | 1439 | 1471 | Muse Spark 1.1 |
| LMArena Text: Chinese | 1481 | 1515 | Muse Spark 1.1 |
| LMArena Text: German | 1458 | 1469 | Muse Spark 1.1 |
| LMArena Text: Japanese | 1446 | 1450 | Muse Spark 1.1 |
| LMArena Text: Korean | 1409 | 1459 | Muse Spark 1.1 |
| LMArena Text: French | 1473 | 1492 | Muse Spark 1.1 |
| LMArena Text: Spanish | 1457 | 1464 | Muse Spark 1.1 |
| LMArena Text: Russian | 1453 | 1482 | Muse Spark 1.1 |
| LMArena Text: Polish | 1461 | 1499 | Muse Spark 1.1 |
| LMArena Text: multi-turn | 1468 | 1484 | Muse Spark 1.1 |
| LMArena Text: longer queries | 1458 | 1462 | Muse Spark 1.1 |
| LMArena Text: writing and language | 1447 | 1448 | Muse Spark 1.1 |
| LMArena Text: entertainment and media | 1431 | 1438 | Muse Spark 1.1 |
| LMArena Vision: English | Not measured | 1292 | Only Muse Spark 1.1 measured |
| LMArena Vision: Chinese | Not measured | 1348 | Only Muse Spark 1.1 measured |
| LMArena Vision: reading text | Not measured | 1301 | Only Muse Spark 1.1 measured |
| LMArena Vision: humor | Not measured | 1288 | Only Muse Spark 1.1 measured |
| LMArena Vision: creative writing | Not measured | 1253 | Only Muse Spark 1.1 measured |
| LMArena Document | Not measured | 1465 | 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 | DeepSeek V4 Pro 0423 | Muse Spark 1.1 | 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
DeepSeek V4 Pro 0423 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Pro 0423 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Pro 0423 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 | DeepSeek V4 Pro 0423 | Meta Muse Spark 1.1 |
|---|---|---|
| Maker | DeepSeek | Meta |
| Weights | Open weights | No public weights listed |
| Released | April 24, 2026 | July 16, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.9553 | $1.25 |
| Output $/Mtok | $1.9105 | $4.25 |
| Coding index | 35.3 | 48.9 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.57 | $0.43 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0423 better than Muse Spark 1.1 for coding?
Pick Muse Spark 1.1 for coding: it scores 48.9 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when output tokens cost 2.2x less, or when what matters is LiveCodeBench (Vals AI) or AA Agentic Index, where it leads.
Which is cheaper, DeepSeek V4 Pro 0423 or Muse Spark 1.1?
DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens; Muse Spark 1.1 costs $1.25 and $4.25. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and Muse Spark 1.1 $0.43.
Which has the bigger context window, DeepSeek V4 Pro 0423 or Muse Spark 1.1?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Pro 0423 vs Muse Spark 1.1 comparison based on?
70 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0423's coding index rests on 1 independent benchmark and Muse Spark 1.1's on 1. Where only one model has a result, the page says so instead of naming a winner.