Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0813 vs Muse Spark 1.3

Updated October 21, 2026. 58 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4 Pro 0813 Replace Muse Spark 1.3
DeepSeek V4 Pro 0813DeepSeek
Coding
54.6
Overall
36.0
Output $/M
$1.98
6
Muse Spark 1.3Meta
Coding
79.7
Overall
48.1
Output $/M
$4.25
50
vs boards won of 58 shared, 2 tied

Decision reading

Pick Muse Spark 1.3 for coding: it scores 79.7 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 when output tokens cost 2.1x less, or when what matters is Terminal-Bench 4 (Vals AI) or Code migration (Vals AI), where it leads.

Model ADeepSeek V4 Pro 0813DeepSeek54.6/1001 independent benchmark$0.10 per solved taskModel BMuse Spark 1.3Meta79.7/1002 independent benchmarksNo cost per solved task
Shared results
58
DeepSeek V4 Pro 0813 only
20
Muse Spark 1.3 only
34
Like-for-like categories
7 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.

At a glance

Coding index
DeepSeek V4 Pro 0813 54.6 from 1 benchmark, Muse Spark 1.3 79.7 from 2 benchmarks.
Widest category
Math, 9.2 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: DeepSeek V4 Pro 0813 26.8% against Muse Spark 1.3 46.3%, 19.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0813 $1.98 against Muse Spark 1.3 $4.25 per million output tokens, 2.1x 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.

Boards won, where both have a result
CategoryDeepSeek V4 Pro 0813BarsMuse Spark 1.3Ties
Coding411
Intelligence02
Agentic work052 ties
Reasoning25
Math06
Knowledge04
General017
All shared boards6502 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index411
Coding benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
LiveBench codingNot measured90.2%Only Muse Spark 1.3 measured
LMArena WebDev15821659Muse Spark 1.3
AA Coding Index68.875.8Muse Spark 1.3
LiveCodeBench (Vals AI)87.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
SWE-bench Verified (Vals AI)96.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
Terminal-Bench 4 (Vals AI)14.1%10.6%DeepSeek V4 Pro 0813
Vibe Code Bench (Vals AI)82.3%82.9%Muse Spark 1.3
Code migration (Vals AI)41.5%27.6%DeepSeek V4 Pro 0813
ProgramBench (Vals AI)0.0%0.5%Muse Spark 1.3
IOI (Vals AI)51.6%43.9%DeepSeek V4 Pro 0813
Terminal-Bench 2.1 (Vals AI)54.7%72.3%Muse Spark 1.3
Vibe Code Bench 1-100 (Vals AI)17.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
SkillsBench (Vals AI)53.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
CyberBench (Vals AI)72.9%69.4%DeepSeek V4 Pro 0813
SciCode51.0%59.7%Muse Spark 1.3
FrontierCode28.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
FrontierSWENot measured25.8%Only Muse Spark 1.3 measured
WeirdML66.2%Not measuredOnly DeepSeek V4 Pro 0813 measured
ALE-Bench1403.21688.3Muse Spark 1.3
LMArena Text: coding14691510Muse Spark 1.3
LMArena Text: software and IT14621511Muse Spark 1.3
LMArena WebDev: React15881672Muse Spark 1.3
LMArena WebDev: HTML15661653Muse Spark 1.3
LMArena WebDev: from an imageNot measured1640Only Muse Spark 1.3 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
AA Intelligence Index36.048.1Muse Spark 1.3
Epoch Capabilities Index155.6157.2Muse Spark 1.3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
AA Agentic Index41.355.5Muse Spark 1.3
Design Arena: agents building web appsNot measured1297Only Muse Spark 1.3 measured
Design Arena: agents building full-stack appsNot measured1295Only Muse Spark 1.3 measured
Design Arena: agents building mobile appsNot measured1217Only Muse Spark 1.3 measured
Design Arena: agents building Godot gamesNot measured1241Only Muse Spark 1.3 measured
Design Arena: PowerPoint slidesNot measured1244Only Muse Spark 1.3 measured
Design Arena: spreadsheetsNot measured1048Only Muse Spark 1.3 measured
LiveBench researchNot measured68.6%Only Muse Spark 1.3 measured
LiveBench browserNot measured80.0%Only Muse Spark 1.3 measured
LiveBench long agenticNot measured40.4%Only Muse Spark 1.3 measured
SREBench (Vals AI)1.9%Not measuredOnly DeepSeek V4 Pro 0813 measured
Finance Agent (Vals AI)50.4%58.9%Muse Spark 1.3
Tax Agent Bench (Vals AI)26.8%36.0%Muse Spark 1.3
Legal Research Bench (Vals AI)40.9%40.9%Tie
Harvey's Legal Agent Benchmark (Vals AI)10.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
Excel Modeling Benchmark (Vals AI)52.8%62.7%Muse Spark 1.3
Terminal-Bench-Science (Vals AI)4.3%4.3%Tie
APEX-Agents47.3%58.6%Muse Spark 1.3
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index25
Reasoning benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
GPQA Diamond92.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
LiveBench reasoningNot measured89.7%Only Muse Spark 1.3 measured
GPQA Diamond (Artificial Analysis run)92.8%94.1%Muse Spark 1.3
Humanity's Last Exam (Artificial Analysis run)41.0%48.7%Muse Spark 1.3
GPQA Diamond (Epoch AI run)91.7%Not measuredOnly DeepSeek V4 Pro 0813 measured
ARC-AGI90.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
ARC-AGI-261.3%Not measuredOnly DeepSeek V4 Pro 0813 measured
Chess puzzles46.0%37.0%DeepSeek V4 Pro 0813
Mystery game puzzles43.0%25.0%DeepSeek V4 Pro 0813
LMArena Text: hard prompts14581503Muse Spark 1.3
LMArena Text: expert14591519Muse Spark 1.3
LMArena Text: hard prompts in English14631500Muse Spark 1.3
LMArena Vision: diagramsNot measured1330Only Muse Spark 1.3 measured
LMArena Vision: homeworkNot measured1296Only Muse Spark 1.3 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
OTIS Mock AIME98.6%99.2%Muse Spark 1.3
FrontierMath, tiers 1 to 364.6%74.4%Muse Spark 1.3
FrontierMath, tier 426.8%46.3%Muse Spark 1.3
ProofBench50.0%58.0%Muse Spark 1.3
LMArena Text: math14411497Muse Spark 1.3
LMArena Text: mathematical work14431491Muse Spark 1.3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
MMLU Pro87.0%Not measuredOnly DeepSeek V4 Pro 0813 measured
LegalBench (Vals AI)82.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
CorpFin (Vals AI)65.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
TaxEval (Vals AI)73.1%Not measuredOnly DeepSeek V4 Pro 0813 measured
MedCode (Vals AI)42.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
SimpleQA Verified52.9%Not measuredOnly DeepSeek V4 Pro 0813 measured
LMArena Text: science14571507Muse Spark 1.3
LMArena Text: medicine and healthcare14461493Muse Spark 1.3
LMArena Text: legal and government14591499Muse Spark 1.3
LMArena Text: business and finance14421490Muse Spark 1.3
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
Design Arena: websitesNot measured1356Only Muse Spark 1.3 measured
Design Arena: UI componentsNot measured1352Only Muse Spark 1.3 measured
Design Arena: game devNot measured1329Only Muse Spark 1.3 measured
Design Arena: data vizNot measured1343Only Muse Spark 1.3 measured
Design Arena: 3DNot measured1359Only Muse Spark 1.3 measured
Design Arena: all code categoriesNot measured1353Only Muse Spark 1.3 measured
Design Arena: SVGNot measured1300Only Muse Spark 1.3 measured
Design Arena: ASCII artNot measured1280Only Muse Spark 1.3 measured
LiveBench designNot measured74.8%Only Muse Spark 1.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
General benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
Vals Index53.0%Not measuredOnly DeepSeek V4 Pro 0813 measured
LiveBench data analysisNot measured79.6%Only Muse Spark 1.3 measured
MedScribe (Vals AI)80.2%Not measuredOnly DeepSeek V4 Pro 0813 measured
Long context reasoning (AA-LCR)80.3%83.0%Muse Spark 1.3
DTBench93.9%96.5%Muse Spark 1.3
LMCA45.5%53.9%Muse Spark 1.3
LMArena Text14461490Muse Spark 1.3
LMArena Text: instruction following14481479Muse Spark 1.3
LMArena Text: creative writing14391462Muse Spark 1.3
LMArena VisionNot measured1308Only Muse Spark 1.3 measured
LMArena Text: English14571495Muse Spark 1.3
LMArena Text: non-English14311481Muse Spark 1.3
LMArena Text: Chinese14811532Muse Spark 1.3
LMArena Text: GermanNot measured1513Only Muse Spark 1.3 measured
LMArena Text: JapaneseNot measured1470Only Muse Spark 1.3 measured
LMArena Text: Korean14491490Muse Spark 1.3
LMArena Text: French14461511Muse Spark 1.3
LMArena Text: Spanish14351496Muse Spark 1.3
LMArena Text: Russian14481491Muse Spark 1.3
LMArena Text: PolishNot measured1490Only Muse Spark 1.3 measured
LMArena Text: multi-turn14541487Muse Spark 1.3
LMArena Text: longer queries14581488Muse Spark 1.3
LMArena Text: writing and language14431470Muse Spark 1.3
LMArena Text: entertainment and media14241457Muse Spark 1.3
LMArena Vision: EnglishNot measured1298Only Muse Spark 1.3 measured
LMArena Vision: ChineseNot measured1384Only Muse Spark 1.3 measured
LMArena Vision: reading textNot measured1319Only Muse Spark 1.3 measured
LMArena Vision: humorNot measured1293Only Muse Spark 1.3 measured
LMArena Vision: creative writingNot measured1296Only Muse Spark 1.3 measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0813 and Muse Spark 1.3
BenchmarkDeepSeek V4 Pro 0813Muse Spark 1.3Leader
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 0813$0.0016Fits in one request
Muse Spark 1.3$0.0034Fits in one request

DeepSeek V4 Pro 0813 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0813$0.039Fits in one request
Muse Spark 1.3$0.075Fits in one request

DeepSeek V4 Pro 0813 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0813$0.152Fits in one request
Muse Spark 1.3$0.292Fits in one request

DeepSeek V4 Pro 0813 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.

Specifications of DeepSeek V4 Pro 0813 and Muse Spark 1.3
SpecificationDeepSeek V4 Pro 0813Meta Muse Spark 1.3
MakerDeepSeekMeta
WeightsOpen weightsNo public weights listed
ReleasedAugust 12, 2026September 2, 2026
Context window1.05M1.05M
Input $/Mtok$0.66$1.25
Output $/Mtok$1.98$4.25
Coding index54.679.7
Independent measurements behind it12
Cost per solved task$0.10Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0813 better than Muse Spark 1.3 for coding?

Pick Muse Spark 1.3 for coding: it scores 79.7 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 2.1x less, or when what matters is Terminal-Bench 4 (Vals AI) or Code migration (Vals AI), where it leads.

Which is cheaper, DeepSeek V4 Pro 0813 or Muse Spark 1.3?

DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; Muse Spark 1.3 costs $1.25 and $4.25. Cost per solved task is known for DeepSeek V4 Pro 0813 only.

Which has the bigger context window, DeepSeek V4 Pro 0813 or Muse Spark 1.3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0813 vs Muse Spark 1.3 comparison based on?

58 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and Muse Spark 1.3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next